© 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. 7-RESID-POST-AA
    11. 10034
    Prev
    Next
    INDEX
    Explanations

    Quoted speech

    np_max-act · gemini-2.0-flash

    It detects sentence-level discourse markers and speaker-focused asides that signal contrast, emphasis, or a shift in stance.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rainfall
    -0.07
    การเล
    -0.06
    (()=>{↵
    -0.06
     Cup
    -0.06
     vene
    -0.06
     gé
    -0.06
     Trick
    -0.06
    ủi
    -0.06
     }],↵
    -0.06
    layan
    -0.06
    POSITIVE LOGITS
    -match
    0.07
    SELF
    0.06
    hoc
    0.06
     match
    0.06
    ??
    0.06
    ้ม
    0.06
     Ко
    0.06
    ีนาคม
    0.06
    MATCH
    0.06
    Anth
    0.06
    Activations Density 0.095%

    No Known Activations