Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42337
    Prev
    Next
    INDEX
    Explanations

    uncertainty

    np_max-act · gemini-2.0-flash

    This neuron spots hedge or speculative cue words (e.g. “perhaps,” “maybe,” etc.) that signal uncertainty or suggestion.

    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
    _keys
    -0.07
     kisses
    -0.07
    dro
    -0.07
     settles
    -0.07
    _indices
    -0.06
     attraction
    -0.06
     Gron
    -0.06
     spoken
    -0.06
     Ethnic
    -0.06
    _count
    -0.06
    POSITIVE LOGITS
     إل
    0.07
     Morr
    0.07
    م
    0.07
    ầm
    0.07
    мовір
    0.06
    .Unlock
    0.06
     tempList
    0.06
     dipl
    0.06
    钮
    0.06
     Perhaps
    0.06
    Activations Density 0.018%

    No Known Activations