© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 19857
    Prev
    Next
    INDEX
    Explanations

    reporting

    np_max-act · gemini-2.0-flash

    content that discusses methods for assessing or evaluating situations, particularly in relation to policies, performance or outcomes.

    oai_token-act-pair · gpt-4o-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
    Back
    -0.07
    _mgr
    -0.06
     Mens
    -0.06
    РО
    -0.06
     pools
    -0.06
    thrown
    -0.06
     internally
    -0.06
     sliding
    -0.06
     Chron
    -0.06
     Barbar
    -0.06
    POSITIVE LOGITS
    мін
    0.08
    imachinery
    0.07
    ِم
    0.07
     kolej
    0.07
    _SYM
    0.06
    _def
    0.06
    icion
    0.06
     succinct
    0.06
    .Schema
    0.06
    +lsi
    0.06
    Activations Density 0.061%

    No Known Activations