© 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 (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 73389
    Prev
    Next
    INDEX
    Explanations

    _trampoline

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uggest
    -0.06
    )NULL
    -0.06
     screaming
    -0.06
     palabras
    -0.06
     всего
    -0.06
    ้องพ
    -0.06
     REPRESENT
    -0.06
    para
    -0.06
    reiben
    -0.05
    herit
    -0.05
    POSITIVE LOGITS
     FixedUpdate
    0.08
    Library
    0.07
    	background
    0.06
     Glouce
    0.06
    .pageSize
    0.06
     zor
    0.06
     downside
    0.06
    .Progress
    0.06
     Pron
    0.06
     salv
    0.06
    Activations Density 0.000%

    No Known Activations