Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 80700
    Prev
    Next
    INDEX
    Explanations

    network

    np_max-act · gemini-2.0-flash

    discussions about research literature and its contributions to a specific field.

    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
     premise
    -0.08
    aldo
    -0.08
    667
    -0.07
    cai
    -0.07
    043
    -0.06
    668
    -0.06
    (vals
    -0.06
    565
    -0.06
    663
    -0.06
    557
    -0.06
    POSITIVE LOGITS
     network
    0.16
     Network
    0.16
    Network
    0.13
     networks
    0.13
    network
    0.13
     Networks
    0.12
     NETWORK
    0.12
    NETWORK
    0.09
    -network
    0.09
    /network
    0.09
    Activations Density 0.032%

    No Known Activations