© 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. 110115
    Prev
    Next
    INDEX
    Explanations

    Object

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on occurrences of the identifier “Object” (in any context or casing).

    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
     bred
    -0.07
     stripes
    -0.07
     tý
    -0.06
     eve
    -0.06
     traversal
    -0.06
     fever
    -0.06
     criter
    -0.06
     května
    -0.06
    干
    -0.06
     Kenny
    -0.06
    POSITIVE LOGITS
     object
    0.14
    Object
    0.13
     objects
    0.12
     Object
    0.12
    object
    0.11
    _obj
    0.11
    obj
    0.10
    .obj
    0.10
    objects
    0.10
     obj
    0.10
    Activations Density 0.060%

    No Known Activations