Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91185
    Prev
    Next
    INDEX
    Explanations

    Finance and economics

    np_max-act · gemini-2.0-flash

    This neuron is triggered by numeric measurements and units (e.g. quantities, dimensions, weights, speeds).

    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
    push
    -0.08
    axis
    -0.07
     frag
    -0.06
     یون
    -0.06
     din
    -0.06
     reco
    -0.06
    xi
    -0.06
     panda
    -0.06
     Pes
    -0.06
    Male
    -0.06
    POSITIVE LOGITS
    (inputs
    0.07
    :])↵
    0.07
    	gr
    0.06
    473
    0.06
    -Un
    0.06
     investigation
    0.06
    decltype
    0.06
    々
    0.06
    Methods
    0.06
     hãy
    0.06
    Activations Density 0.045%

    No Known Activations