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. 83485
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
     Dirty
    -0.07
     ques
    -0.07
    Good
    -0.07
     Toilet
    -0.07
                                      
    -0.07
     Rid
    -0.06
    asd
    -0.06
     melodies
    -0.06
     reassure
    -0.06
    ाँ
    -0.06
    POSITIVE LOGITS
    ascii
    0.06
    rench
    0.06
    _splits
    0.06
    rox
    0.06
    StrLn
    0.06
    neys
    0.06
    antage
    0.06
    elder
    0.06
    uluk
    0.06
     SEX
    0.06
    Activations Density 0.013%

    No Known Activations