© 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. 44414
    Prev
    Next
    INDEX
    Explanations

    real

    np_max-act · gemini-2.0-flash

    This neuron activates on the standalone token “Real,” as in “Real-time,” “Real Estate,” “Real disposable income,” etc.

    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
     Judith
    -0.07
     Snyder
    -0.07
     doprov
    -0.07
     dosy
    -0.07
     Chamber
    -0.07
    ubu
    -0.07
     podrob
    -0.07
     July
    -0.07
     Grove
    -0.07
     supplying
    -0.07
    POSITIVE LOGITS
     real
    0.16
     Real
    0.15
    real
    0.14
    Real
    0.13
     REAL
    0.11
    REAL
    0.10
    al
    0.10
    ал
    0.09
    AL
    0.09
    _Real
    0.09
    Activations Density 0.029%

    No Known Activations