© 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. 29956
    Prev
    Next
    INDEX
    Explanations

    accused

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on verbs related to applying or blaming—specifically occurrences of “use” (and its forms like “using”) and “accuse” (and its inflections).

    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
    _Length
    -0.07
     fullWidth
    -0.07
     влаж
    -0.07
     développement
    -0.07
    /St
    -0.07
    _St
    -0.07
     佛
    -0.06
     fetal
    -0.06
    flen
    -0.06
     Survival
    -0.06
    POSITIVE LOGITS
     accused
    0.13
     accuse
    0.13
     accusing
    0.11
     accusation
    0.11
     accus
    0.11
     accusations
    0.10
     accuses
    0.10
     Acc
    0.09
    оком
    0.08
     evacuate
    0.08
    Activations Density 0.005%

    No Known Activations