© 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. 91558
    Prev
    Next
    INDEX
    Explanations

    ol

    np_max-act · gemini-2.0-flash

    This neuron activates on the characteristic “-ol”/“-ite” suffix in chemical names—i.e., it detects mentions of zeolite (and related “-ite”) framework materials.

    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
    .NoArgsConstructor
    -0.07
    ,、
    -0.07
     SZ
    -0.06
    .maven
    -0.06
     Craw
    -0.06
     όταν
    -0.06
    .gender
    -0.06
    Bulk
    -0.06
     Barn
    -0.06
     asn
    -0.06
    POSITIVE LOGITS
    	prev
    0.07
     Cho
    0.07
     acceptable
    0.07
     Type
    0.07
    stringLiteral
    0.07
    John
    0.06
     consumed
    0.06
    ONLY
    0.06
    ?:
    0.06
    _TEMPLATE
    0.06
    Activations Density 0.001%

    No Known Activations