© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129836
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    This neuron detects short phrases serving as Markdown-style section or subsection headings.

    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
    refresh
    -0.07
     knees
    -0.06
    .detectChanges
    -0.06
    toPromise
    -0.06
    Company
    -0.06
     amusement
    -0.06
    ену
    -0.06
    �
    -0.06
    πλα
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    Else
    0.07
     christian
    0.07
     undoubtedly
    0.06
     Cutting
    0.06
    _working
    0.06
    _der
    0.06
    Thus
    0.06
     prise
    0.06
    side
    0.06
     gần
    0.06
    Activations Density 0.062%

    No Known Activations