© 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. 126189
    Prev
    Next
    INDEX
    Explanations

    real acceptable

    np_max-act · gemini-2.0-flash

    The neuron identifies evaluative adjectives that signal authenticity, approval, or desirability (e.g. “valid,” “legitimate,” “desired”).

    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
    Before
    -0.06
    ooo
    -0.06
    icit
    -0.06
     всех
    -0.06
    .blit
    -0.06
     авт
    -0.05
    "If
    -0.05
     coin
    -0.05
    ælland
    -0.05
    Erro
    -0.05
    POSITIVE LOGITS
     �
    0.07
     cle
    0.07
    uluk
    0.07
     その他
    0.07
    -origin
    0.07
     regarded
    0.07
    gle
    0.07
    -contained
    0.06
    urring
    0.06
     režim
    0.06
    Activations Density 0.017%

    No Known Activations