© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30011
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash

    The neuron responds to occurrences of the auxiliary/linking verb “be” (and closely related modal‐auxiliary constructions like “can be”).

    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
    (head
    -0.07
    θρώ
    -0.06
    ]';↵
    -0.06
     rescued
    -0.06
     تف
    -0.06
     στο
    -0.06
            
    ↵        
    ↵
    -0.06
     відмов
    -0.06
     besteht
    -0.06
    .Per
    -0.06
    POSITIVE LOGITS
     mw
    0.07
     padr
    0.07
     déjà
    0.07
    vlc
    0.07
    kw
    0.07
    =query
    0.07
    admin
    0.07
     cultiv
    0.07
    -hour
    0.06
    _NON
    0.06
    Activations Density 0.026%

    No Known Activations