© 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. 42771
    Prev
    Next
    INDEX
    Explanations

    punctuation and common words

    np_max-act · gemini-2.0-flash

    The neuron detects discourse cues that introduce positive or solution‐oriented statements (e.g. “the good news is:”, “but it’s not just…”).

    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
     spectators
    -0.06
     enquiries
    -0.06
     owning
    -0.06
    -vector
    -0.06
    778
    -0.06
     mnoha
    -0.06
     rotary
    -0.06
     recycled
    -0.06
    。この
    -0.06
     telecom
    -0.06
    POSITIVE LOGITS
     }
↵
↵
↵
    0.07
    णन
    0.07
     Alt
    0.06
     demise
    0.06
     GetString
    0.06
    igators
    0.06
    _Zero
    0.06
    할
    0.06
    ık
    0.06
     alacak
    0.06
    Activations Density 0.115%

    No Known Activations