© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68574
    Prev
    Next
    INDEX
    Explanations

    speak

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on occurrences of the verb “speak” (and its inflected forms).

    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
     Madd
    -0.07
     hardened
    -0.07
    INT
    -0.07
    altet
    -0.07
    .currentTimeMillis
    -0.07
     adding
    -0.07
    Ty
    -0.07
    Td
    -0.06
    Lint
    -0.06
    urpose
    -0.06
    POSITIVE LOGITS
     speak
    0.13
     speaking
    0.12
     Speak
    0.11
     speaks
    0.11
     spoken
    0.11
     speaker
    0.10
     Speech
    0.10
    Speak
    0.10
    spe
    0.09
     Speaking
    0.09
    Activations Density 0.031%

    No Known Activations