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. 15-RESID-POST-AA
    6. 121916
    Prev
    Next
    INDEX
    Explanations

    9/11 related texts

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impunity
    -0.07
    -len
    -0.07
     Merkel
    -0.07
     Cialis
    -0.07
    狐
    -0.06
    Controller
    -0.06
    Branch
    -0.06
    .cpu
    -0.06
    示
    -0.06
     Qed
    -0.06
    POSITIVE LOGITS
    ')";↵
    0.07
     Lighting
    0.07
    /qu
    0.07
     Lit
    0.06
     komunik
    0.06
    cím
    0.06
     stan
    0.06
    gallery
    0.06
     }
    ↵
    ↵
    ↵
    0.06
    رخ
    0.06
    Activations Density 0.004%

    No Known Activations