© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91567
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron detects descriptive phrases signaling a broad scope or variety—e.g. “wide range of applications.”

    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
     stopwords
    -0.07
     centroids
    -0.06
     männ
    -0.06
     corpor
    -0.06
    HEN
    -0.06
     />}
    -0.06
     Πο
    -0.06
    ільки
    -0.06
     حتی
    -0.06
    悉
    -0.06
    POSITIVE LOGITS
     kaz
    0.07
     �
    0.07
     expanding
    0.07
     wake
    0.06
    -web
    0.06
    <<
    0.06
    속
    0.06
     рост
    0.06
     zou
    0.06
     změn
    0.06
    Activations Density 0.014%

    No Known Activations