© 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. 89805
    Prev
    Next
    INDEX
    Explanations

    acid

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of chemical acids, particularly occurrences of “acid” at the end of compound names.

    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
    noop
    -0.08
    Che
    -0.07
     můž
    -0.07
    LO
    -0.07
    .compose
    -0.07
    FTER
    -0.07
    周
    -0.07
    getClient
    -0.07
     �
    -0.07
     luôn
    -0.07
    POSITIVE LOGITS
     acid
    0.16
     Acid
    0.14
     acids
    0.12
    acid
    0.09
     ac
    0.08
     Ac
    0.08
    _AF
    0.08
     acidity
    0.07
     AC
    0.07
    xia
    0.07
    Activations Density 0.020%

    No Known Activations