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. 7-RESID-POST-AA
    6. 36326
    Prev
    Next
    INDEX
    Explanations

    blood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     أح
    -0.07
    _atom
    -0.06
    _TA
    -0.06
    _UNDEF
    -0.06
     där
    -0.06
     صف
    -0.06
     کودکان
    -0.06
    .am
    -0.06
    “He
    -0.06
    _with
    -0.06
    POSITIVE LOGITS
     getColor
    0.06
     Typ
    0.06
    osite
    0.06
     getIndex
    0.06
    NH
    0.06
     PropTypes
    0.06
     pixels
    0.06
     PAN
    0.06
     handleError
    0.06
    	std
    0.06
    Activations Density 0.008%

    No Known Activations