© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 90841
    Prev
    Next
    INDEX
    Explanations

    Conversational narrative

    np_max-act · gemini-2.0-flash

    This neuron detects meta-linguistic hedging and intensity comments—phrases where the writer evaluates or softens word choice (e.g. “too strong a word,” “probably a better word,” “might be a bit misleading”).

    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
     histograms
    -0.07
     optimizer
    -0.07
     beating
    -0.07
    akte
    -0.06
    Filled
    -0.06
     vlak
    -0.06
     sampling
    -0.06
     zad
    -0.06
     rectangle
    -0.06
     arrested
    -0.06
    POSITIVE LOGITS
    RELATED
    0.06
     thiết
    0.06
     �
    0.06
    osl
    0.06
    icos
    0.06
    Ctrls
    0.06
    ansas
    0.06
     Libyan
    0.06
    AndServe
    0.06
     населення
    0.06
    Activations Density 0.023%

    No Known Activations