© 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. 93472
    Prev
    Next
    INDEX
    Explanations

    Microsoft

    np_max-act · gemini-2.0-flash

    names of technology companies and their products.

    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
    an
    -0.08
     AN
    -0.08
     dayan
    -0.06
     Bone
    -0.06
    연
    -0.06
    _penalty
    -0.06
    ,N
    -0.06
    -plan
    -0.06
     Hay
    -0.06
    :A
    -0.06
    POSITIVE LOGITS
     Microsoft
    0.15
    Microsoft
    0.14
    .Microsoft
    0.09
     microsoft
    0.09
    milliseconds
    0.08
    issa
    0.08
    Cisco
    0.08
    icrosoft
    0.08
     Cisco
    0.08
     Micro
    0.08
    Activations Density 0.008%

    No Known Activations