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. 106755
    Prev
    Next
    INDEX
    Explanations

    Remembering

    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
    _CB
    -0.06
    ecs
    -0.06
                                                                            
    -0.06
    (Post
    -0.06
     آسی
    -0.06
    าประ
    -0.06
    沃
    -0.05
     itch
    -0.05
     rempl
    -0.05
     Casc
    -0.05
    POSITIVE LOGITS
    .assign
    0.07
    üyor
    0.07
    ({'
    0.07
    样子
    0.07
    ------↵
    0.06
    .Status
    0.06
     Mate
    0.06
     authentication
    0.06
    imate
    0.06
     Terry
    0.06
    Activations Density 0.028%

    No Known Activations