© 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. 125205
    Prev
    Next
    INDEX
    Explanations

    gibberish

    np_max-act · gemini-2.0-flash

    The neuron is essentially tracking how far into a continuous text block you are—its activation rises as you move deeper into a long span of text and falls near the beginnings and ends.

    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
    ipa
    -0.07
     dirty
    -0.07
     Kids
    -0.07
    GPL
    -0.07
    Kids
    -0.06
    MPI
    -0.06
    agas
    -0.06
     impl
    -0.06
    人が
    -0.06
    })();
    -0.06
    POSITIVE LOGITS
     Ha
    0.06
     будинку
    0.06
     /(
    0.06
     nostalgic
    0.06
    >j
    0.05
    下来
    0.05
    ‌است
    0.05
     Sho
    0.05
     tư
    0.05
     hey
    0.05
    Activations Density 0.025%

    No Known Activations