© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7931
    Prev
    Next
    INDEX
    Explanations

    river flow descriptions

    np_max-act · gemini-2.0-flash

    information about rivers and their characteristics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on words and phrases describing how one river connects to another (e.g. “tributary of,” “flows into,” “confluence,” “discharges into”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vari
    -0.07
    ляється
    -0.07
    },{
    -0.06
    rip
    -0.06
     Shame
    -0.06
    lineno
    -0.06
     Cup
    -0.06
     awarded
    -0.06
    hand
    -0.06
    ление
    -0.06
    POSITIVE LOGITS
    .Extension
    0.07
     servic
    0.07
     NotSupportedException
    0.07
    ULA
    0.07
    _batches
    0.06
    _init
    0.06
    DELETE
    0.06
    UsingEncoding
    0.06
    _SECRET
    0.06
    :Register
    0.06
    Activations Density 0.007%

    No Known Activations