© 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. 92483
    Prev
    Next
    INDEX
    Explanations

    >=

    np_max-act · gemini-2.0-flash

    The neuron is keyed to decimal numbers with non‐zero fractional parts (e.g. the “.xxxxx” in version specs).

    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
    ValueType
    -0.07
     resin
    -0.06
     сай
    -0.06
    大き
    -0.06
     oci
    -0.06
     isl
    -0.06
    μφωνα
    -0.06
     malfunction
    -0.06
    RoutingModule
    -0.06
     멀
    -0.06
    POSITIVE LOGITS
     Russ
    0.07
     EG
    0.06
    TE
    0.06
     Brendan
    0.06
     Megan
    0.06
     Sacred
    0.06
    query
    0.06
    利
    0.06
    е
    0.06
    και
    0.06
    Activations Density 0.001%

    No Known Activations