© 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. 72755
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    specific applications or tools related to business processes.

    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
     cud
    -0.07
    شر
    -0.06
    였
    -0.06
     coping
    -0.06
    ��
    -0.06
     grooming
    -0.06
     boxes
    -0.06
    .additional
    -0.06
    quotelev
    -0.06
    Speaking
    -0.06
    POSITIVE LOGITS
     získat
    0.07
    ellan
    0.06
     ruby
    0.06
    TRACE
    0.06
    dhcp
    0.06
     Authentic
    0.06
     Laravel
    0.06
    `='$
    0.06
    {{{
    0.06
    (util
    0.06
    Activations Density 0.123%

    No Known Activations