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. 110552
    Prev
    Next
    INDEX
    Explanations

    suffixes ive and ational

    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
     HelloWorld
    -0.08
     Generally
    -0.07
     hust
    -0.06
     Gaul
    -0.06
     revoke
    -0.06
    	i
    -0.06
    InstantiationException
    -0.06
     Offering
    -0.06
    plevel
    -0.06
    .nativeElement
    -0.06
    POSITIVE LOGITS
    puties
    0.06
     packageName
    0.06
    obo
    0.06
     retains
    0.06
    ipation
    0.06
    örü
    0.06
    utf
    0.06
     novels
    0.06
    part
    0.06
     помощ
    0.06
    Activations Density 0.102%

    No Known Activations