© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 30488
    Prev
    Next
    INDEX
    Explanations

    regarding to

    np_max-act · gemini-2.0-flash

    signals content about illegal dangerous or policy sensitive topics such as weapons explosives child exploitation sexual public activity and related legal or safety concerns

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     marginalized
    -0.07
    Checksum
    -0.07
    alg
    -0.07
    ensaje
    -0.07
    ELSE
    -0.07
     yo
    -0.06
     울
    -0.06
    reach
    -0.06
    यन
    -0.06
     enzym
    -0.06
    POSITIVE LOGITS
    čního
    0.06
    (regex
    0.06
     lekker
    0.06
    ň
    0.06
    hled
    0.06
    krát
    0.06
    十八
    0.06
     Cairo
    0.06
    ",$
    0.06
    (string
    0.06
    Activations Density 0.028%

    No Known Activations