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. 74125
    Prev
    Next
    INDEX
    Explanations

    may

    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
     efect
    -0.06
     adjacency
    -0.06
     designation
    -0.06
     nichž
    -0.06
    ulares
    -0.06
    enuity
    -0.06
    challenge
    -0.06
     вклад
    -0.06
    _OBJ
    -0.06
    ceu
    -0.06
    POSITIVE LOGITS
     directional
    0.07
     should
    0.07
    伝
    0.07
     )
    ↵
    0.07
    —
    0.07
    dataArray
    0.06
     semif
    0.06
     doses
    0.06
     unins
    0.06
    ensen
    0.06
    Activations Density 0.160%

    No Known Activations