© 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. 42757
    Prev
    Next
    INDEX
    Explanations

    NSFW content

    np_max-act · gemini-2.0-flash

    This neuron detects the character sequence “anal” (as in words like “anal,” “anime anal,” etc.).

    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
    ังคม
    -0.07
    Define
    -0.07
    iệ
    -0.06
     embeddings
    -0.06
    	with
    -0.06
    ectl
    -0.06
     Charges
    -0.06
    OOT
    -0.06
     alph
    -0.06
    ียก
    -0.06
    POSITIVE LOGITS
    override
    0.06
     органи
    0.06
     rugged
    0.06
     matte
    0.06
     PST
    0.06
    ाध
    0.06
     register
    0.05
     secondary
    0.05
    ICY
    0.05
    composer
    0.05
    Activations Density 0.002%

    No Known Activations