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. 23-RESID-POST-AA
    6. 40655
    Prev
    Next
    INDEX
    Explanations

    Chemical compounds with numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,.
    -0.07
     q
    -0.07
     phrase
    -0.06
     PLAYER
    -0.06
    lake
    -0.06
    sounds
    -0.06
     pounding
    -0.06
     Dry
    -0.06
     Killed
    -0.06
     list
    -0.06
    POSITIVE LOGITS
    +%
    0.07
    τσ
    0.07
     PKK
    0.07
     раза
    0.07
    .lastIndexOf
    0.07
    ",&
    0.07
    DXVECTOR
    0.07
     sharedInstance
    0.07
    OperationContract
    0.07
     Κό
    0.07
    Activations Density 0.015%

    No Known Activations