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. 124735
    Prev
    Next
    INDEX
    Explanations

    to and from

    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
     aid
    -0.07
     prison
    -0.07
    /contact
    -0.07
     kredi
    -0.06
     share
    -0.06
     dart
    -0.06
     Prison
    -0.06
     passwords
    -0.06
    	await
    -0.06
     abyss
    -0.06
    POSITIVE LOGITS
     fauna
    0.07
     Whats
    0.07
     bồi
    0.07
    noc
    0.06
    _nonce
    0.06
    _CHARSET
    0.06
    ALIGN
    0.06
    ¥
    0.06
     Київ
    0.06
     bree
    0.06
    Activations Density 0.018%

    No Known Activations