© 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. 90674
    Prev
    Next
    INDEX
    Explanations

    legal dismissals and restrictions

    np_max-act · gemini-2.0-flash

    The neuron flags statutory citation lines and “three‐strikes” / in forma pauperis code references (e.g. 28 U.S.C. § 1915 and its subsections).

    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
    انی
    -0.07
    _bold
    -0.07
    porter
    -0.06
    umped
    -0.06
     mic
    -0.06
    .SetToolTip
    -0.06
    ог
    -0.06
    év
    -0.06
     belts
    -0.06
    -weight
    -0.06
    POSITIVE LOGITS
     skoro
    0.06
    =context
    0.06
    _wait
    0.06
     SCIP
    0.06
    _periods
    0.06
     dnes
    0.06
    adaptive
    0.06
     Clerk
    0.06
     Codable
    0.06
    984
    0.06
    Activations Density 0.004%

    No Known Activations