© 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. 73099
    Prev
    Next
    INDEX
    Explanations

    Forum questions and answers

    np_max-act · gemini-2.0-flash

    instructions or jailbreak-style commands that demand the model follow a user's orders or enable an alternate/unrestricted mode.

    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_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
    /do
    -0.07
     tty
    -0.06
    --+
    -0.06
    /ref
    -0.06
    (Test
    -0.06
    SPEC
    -0.06
     сю
    -0.06
     IQ
    -0.06
    (serial
    -0.06
    (geometry
    -0.06
    POSITIVE LOGITS
    олод
    0.07
    akter
    0.07
     servant
    0.07
     paced
    0.06
    ك
    0.06
     lä
    0.06
     detecting
    0.06
     Vice
    0.06
     metabolism
    0.06
     tapped
    0.06
    Activations Density 0.001%

    No Known Activations