© 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. 30586
    Prev
    Next
    INDEX
    Explanations

    Fact

    np_max-act · gemini-2.0-flash

    The neuron activates on unit‐test attribute annotations (e.g. the “[Fact]” and “[Theory]” markers).

    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
    Demon
    -0.06
     نو
    -0.06
    \Exceptions
    -0.06
     otherButtonTitles
    -0.06
     IntPtr
    -0.06
     Serializer
    -0.06
     budd
    -0.06
     lm
    -0.06
    .Popen
    -0.06
    IntoConstraints
    -0.06
    POSITIVE LOGITS
     Greece
    0.07
     地
    0.06
     visuals
    0.06
    еление
    0.06
    ODULE
    0.06
    ateral
    0.06
     benef
    0.06
     pathological
    0.06
     favored
    0.06
    	require
    0.06
    Activations Density 0.004%

    No Known Activations