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. 111816
    Prev
    Next
    INDEX
    Explanations

    Thoughts/Questions

    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
    enk
    -0.07
    BP
    -0.07
     Со
    -0.06
    _multip
    -0.06
     BP
    -0.06
     отп
    -0.06
    lear
    -0.06
     BLE
    -0.06
    _DISABLED
    -0.06
     noc
    -0.06
    POSITIVE LOGITS
    OwnerId
    0.07
     %=
    0.07
    .atan
    0.07
    };
    ↵
    0.06
    Und
    0.06
    Cit
    0.06
    	parser
    0.06
    gebn
    0.06
    #{@
    0.06
     Ed
    0.06
    Activations Density 0.020%

    No Known Activations