© 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. 15-RESID-POST-AA
    11. 71584
    Prev
    Next
    INDEX
    Explanations

    informal writing

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on explicit sexual/pornographic content—especially graphic sexual acts and abusive or underage sexual scenarios.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     çal
    -0.07
     فول
    -0.06
    Tracker
    -0.06
     застосов
    -0.06
     undermin
    -0.06
     سن
    -0.06
     Ül
    -0.06
    .way
    -0.06
    Sh
    -0.06
     Raw
    -0.06
    POSITIVE LOGITS
    acimiento
    0.07
    saldo
    0.07
    ]?
    0.07
    ---------↵
    0.07
    احل
    0.07
    _".$
    0.07
    .epam
    0.06
     outlaw
    0.06
     strtok
    0.06
     practices
    0.06
    Activations Density 0.342%

    No Known Activations