© 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. 15-RESID-POST-AA
    11. 40914
    Prev
    Next
    INDEX
    Explanations

    company and innovation

    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
    MAIL
    -0.06
    uu
    -0.06
    machine
    -0.06
    orial
    -0.06
    akh
    -0.06
    ملكة
    -0.06
     rh
    -0.06
     didSelectRowAtIndexPath
    -0.05
    CFG
    -0.05
    ipp
    -0.05
    POSITIVE LOGITS
                ↵↵
    0.07
    ・・・↵↵
    0.07
     виконав
    0.07
     dbl
    0.07
    .Start
    0.06
    -start
    0.06
            
↵
↵
    0.06
    '];
↵
↵
    0.06
    		↵
    0.06
     exhibitions
    0.06
    Activations Density 0.091%

    No Known Activations