© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89040
    Prev
    Next
    INDEX
    Explanations

    Code/logs/filepaths

    np_max-act · gemini-2.0-flash

    The neuron is specializing in spotting shell‐prompt strings (e.g. username@host or related user/directory tokens in a command‐line log).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    directories
    -0.06
    oxy
    -0.06
    -specific
    -0.06
    Bar
    -0.06
    ’
    -0.06
     invading
    -0.06
     purch
    -0.06
     첨부
    -0.06
    ूद
    -0.06
     jsme
    -0.06
    POSITIVE LOGITS
     ENTER
    0.06
     AIDS
    0.06
     �
    0.06
    .localScale
    0.06
    优
    0.06
     Верхов
    0.06
    _ATOMIC
    0.06
     Develop
    0.06
    slu
    0.06
     HK
    0.06
    Activations Density 0.007%

    No Known Activations