© 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. 29955
    Prev
    Next
    INDEX
    Explanations

    relative

    np_max-act · gemini-2.0-flash

    This neuron specializes in detecting occurrences of the word “relative” and related patterns indicating relative motion or displacement.

    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
    dden
    -0.07
     hra
    -0.06
    detach
    -0.06
     toi
    -0.06
    LDAP
    -0.06
    认为
    -0.06
    前
    -0.06
     بعضی
    -0.06
    ele
    -0.06
    Ι
    -0.06
    POSITIVE LOGITS
     cultured
    0.07
    .CSS
    0.07
     relative
    0.06
     selection
    0.06
     rates
    0.06
    _ratio
    0.06
     Probability
    0.06
    .relative
    0.06
     rate
    0.06
    utation
    0.06
    Activations Density 0.004%

    No Known Activations