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. 19-RESID-POST-AA
    6. 83621
    Prev
    Next
    INDEX
    Explanations

    18

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lıyor
    -0.07
     V
    -0.07
     V
    -0.06
     L
    -0.06
     února
    -0.06
    !/
    -0.06
    Statement
    -0.06
    	P
    -0.06
    	l
    -0.06
     yazar
    -0.06
    POSITIVE LOGITS
    Arena
    0.06
     مس
    0.06
    CEPT
    0.06
     گن
    0.06
     minister
    0.06
    .variables
    0.06
     Bethesda
    0.06
     информ
    0.06
    164
    0.06
    -mask
    0.06
    Activations Density 0.000%

    No Known Activations