© 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. 7-RESID-POST-AA
    11. 71892
    Prev
    Next
    INDEX
    Explanations

    symptoms

    np_max-act · gemini-2.0-flash

    discussions of poisoning/toxicity, including exposure, symptoms, severity/lethality, and related medical or veterinary treatment.

    oai_token-act-pair · gpt-5Triggered 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
     shifting
    -0.06
     counter
    -0.06
    teil
    -0.06
     conversation
    -0.06
     wheelchair
    -0.06
     landscapes
    -0.06
     basin
    -0.06
     resilient
    -0.06
    vironments
    -0.06
     ecosystems
    -0.06
    POSITIVE LOGITS
    atalog
    0.06
     заяв
    0.06
     DataContext
    0.06
    alth
    0.06
    ('-',
    0.06
    -question
    0.06
    メリカ
    0.06
    roker
    0.06
    asterxml
    0.06
     Marx
    0.06
    Activations Density 0.026%

    No Known Activations