© 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. 42576
    Prev
    Next
    INDEX
    Explanations

    .amazonaws

    np_max-act · gemini-2.0-flash

    This neuron activates on parts of URLs pointing to Amazon S3 (amazonaws.com) static‐resource hosts.

    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
    _articles
    -0.06
     MaterialPageRoute
    -0.06
    6
    -0.06
    DisplayStyle
    -0.06
    	br
    -0.06
    i
    -0.06
     司
    -0.06
     specular
    -0.06
    VIDIA
    -0.06
    .pic
    -0.05
    POSITIVE LOGITS
     Autonomous
    0.09
     autonomous
    0.07
    .amazonaws
    0.07
    odian
    0.07
     hacks
    0.07
    utilities
    0.07
    、“
    0.07
    ากาศ
    0.07
    omic
    0.06
    _FUNCTION
    0.06
    Activations Density 0.000%

    No Known Activations