© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56023
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron responds to special formatting and boundary markers (e.g. quotation marks, start/end identifiers) rather than the actual content.

    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
     Eduardo
    -0.06
     Hydraulic
    -0.06
     laat
    -0.06
    ductory
    -0.06
    	tree
    -0.05
    .bukkit
    -0.05
     educ
    -0.05
     Buccane
    -0.05
    chimp
    -0.05
    [from
    -0.05
    POSITIVE LOGITS
    NoSuch
    0.07
    ENCIES
    0.07
    .Players
    0.07
    lech
    0.07
    었
    0.07
    .NewReader
    0.07
    ност
    0.06
    ãn
    0.06
    ')),
    0.06
    "))
    0.06
    Activations Density 0.219%

    No Known Activations