© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91534
    Prev
    Next
    INDEX
    Explanations

    correctness

    np_max-act · gemini-2.0-flash

    topics related to healthcare and cancer treatment issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on evaluative adverbs and qualifiers expressing judgment or stance (e.g. “correctly,” “justified,” “rightly”).

    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
     shameful
    -0.07
    -placeholder
    -0.07
    .Build
    -0.06
     mural
    -0.06
     propose
    -0.06
     vetor
    -0.06
    Activate
    -0.06
    /editor
    -0.06
     deny
    -0.06
    드로
    -0.06
    POSITIVE LOGITS
    ียนบ
    0.06
    "]]↵
    0.06
    овая
    0.06
     endangered
    0.06
    ocurrency
    0.06
    /k
    0.06
    rod
    0.06
    .internet
    0.06
     đô
    0.06
     zorun
    0.06
    Activations Density 0.025%

    No Known Activations