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. 3-RESID-POST-AA
    6. 94320
    Prev
    Next
    INDEX
    Explanations

    Rolling Stone

    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
     repent
    -0.07
    fall
    -0.06
     Champ
    -0.06
     お
    -0.06
     murderous
    -0.06
    :::::::
    -0.06
    Fade
    -0.06
     surfaced
    -0.06
     twists
    -0.05
     lacks
    -0.05
    POSITIVE LOGITS
     Stones
    0.16
     Stone
    0.08
     stones
    0.08
    modern
    0.08
    qq
    0.07
    _mean
    0.07
    deserialize
    0.07
     verr
    0.07
    _lazy
    0.07
     securities
    0.06
    Activations Density 0.002%

    No Known Activations