© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 97845
    Prev
    Next
    INDEX
    Explanations

    to

    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
    gest
    -0.07
     offences
    -0.06
    ského
    -0.06
     tarih
    -0.06
     économ
    -0.06
     TORT
    -0.06
    expired
    -0.06
    Woman
    -0.06
    องค
    -0.06
    notes
    -0.06
    POSITIVE LOGITS
    IJ
    0.07
    .NO
    0.06
    くと
    0.06
     interventions
    0.06
     getRequest
    0.06
    ่าส
    0.06
    rik
    0.06
                    ↵↵
    0.06
     Phú
    0.06
    毕业
    0.06
    Activations Density 0.006%

    No Known Activations