© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90776
    Prev
    Next
    INDEX
    Explanations

    written works

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that belong to the titles or headings of scholarly works (e.g. book or paper titles).

    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
     title
    -0.07
     hai
    -0.07
     cient
    -0.06
     vg
    -0.06
    ă
    -0.06
    .stream
    -0.06
    (interface
    -0.06
     amplifier
    -0.06
    uing
    -0.06
    wd
    -0.06
    POSITIVE LOGITS
    .savetxt
    0.07
    式会社
    0.06
     PreparedStatement
    0.06
     athleticism
    0.06
    writing
    0.06
    	↵↵
    0.06
    ροφορίες
    0.06
    Mutable
    0.06
     multiprocessing
    0.06
     vrouwen
    0.06
    Activations Density 0.152%

    No Known Activations