© 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. 11-RESID-POST-AA
    11. 26047
    Prev
    Next
    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash

    queries related to medical conditions and their consequences.

    oai_token-act-pair · gpt-4o-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
     Ford
    -0.08
     DL
    -0.07
     EDM
    -0.07
     morale
    -0.07
    リ
    -0.06
    orro
    -0.06
    864
    -0.06
     DLL
    -0.06
    Destroy
    -0.06
    PL
    -0.06
    POSITIVE LOGITS
     questions
    0.14
     question
    0.14
     Question
    0.12
     Questions
    0.11
    questions
    0.11
     QUESTION
    0.11
    Questions
    0.11
    question
    0.10
     вопрос
    0.09
     ques
    0.09
    Activations Density 0.086%

    No Known Activations