© 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. 7-RESID-POST-AA
    6. 120386
    Prev
    Next
    INDEX
    Explanations

    endangered species/wildlife

    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
    *scale
    -0.07
     parents
    -0.06
     alerted
    -0.06
     euch
    -0.06
    [port
    -0.06
     paying
    -0.06
    SPARENT
    -0.06
     Trevor
    -0.06
     문제
    -0.06
     спроб
    -0.06
    POSITIVE LOGITS
    ."
    ↵
    0.09
     HinderedRotor
    0.07
     MouseEventArgs
    0.07
    olum
    0.07
     heterogeneous
    0.06
    _ov
    0.06
    Month
    0.06
     volver
    0.06
    ΙΟ
    0.06
    	pp
    0.06
    Activations Density 0.015%

    No Known Activations