© 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. 88117
    Prev
    Next
    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash

    The neuron consistently fires on the discourse add-on adverb “also.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to architectural features and artistic representations in classical influences.

    oai_token-act-pair · gpt-4o-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
    nat
    -0.07
     Minute
    -0.06
    int
    -0.06
     till
    -0.06
    341
    -0.06
     tired
    -0.06
    	wg
    -0.06
     Mant
    -0.06
    QUARE
    -0.06
     Trent
    -0.06
    POSITIVE LOGITS
     also
    0.22
    also
    0.16
     Also
    0.15
     ALSO
    0.13
    Also
    0.12
     نیز
    0.11
     também
    0.10
     ebenfalls
    0.10
     additionally
    0.10
     likewise
    0.10
    Activations Density 0.126%

    No Known Activations