© 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. 3-RESID-POST-AA
    11. 121931
    Prev
    Next
    INDEX
    Explanations

    one

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     courtyard
    -0.07
     abort
    -0.07
     ягод
    -0.07
     ecx
    -0.06
    _sp
    -0.06
    .two
    -0.06
    publication
    -0.06
    	diff
    -0.06
     Az
    -0.06
    Forever
    -0.06
    POSITIVE LOGITS
    1
    0.09
    畫
    0.07
    или
    0.07
    -One
    0.07
    idal
    0.06
    /m
    0.06
    si
    0.06
    楽し
    0.06
    casts
    0.06
     hardly
    0.06
    Activations Density 0.097%

    No Known Activations