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. 42212
    Prev
    Next
    INDEX
    Explanations

    Internet text excerpts

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive on ordinary text and does not detect any of the shown tokens.

    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
    	AL
    -0.07
     pants
    -0.07
     PT
    -0.07
    LineStyle
    -0.07
     dsp
    -0.06
    IFT
    -0.06
     кня
    -0.06
    ARI
    -0.06
     XY
    -0.06
    ]]></
    -0.06
    POSITIVE LOGITS
    biology
    0.07
    .fromString
    0.07
     уже
    0.06
     pobl
    0.06
    ',
    0.06
    이야
    0.06
    물을
    0.06
     FormBuilder
    0.06
    	TokenName
    0.06
     squeeze
    0.06
    Activations Density 0.013%

    No Known Activations