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. 40530
    Prev
    Next
    INDEX
    Explanations

    NSS

    np_max-act · gemini-2.0-flash

    the presence of uppercase abbreviations or acronyms (initialisms) in the text

    oai_token-act-pair · o4-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
    10
    -0.10
    15
    -0.09
    7
    -0.09
    20
    -0.09
    800
    -0.08
    100
    -0.08
    13
    -0.08
    31
    -0.08
    395
    -0.08
    4
    -0.08
    POSITIVE LOGITS
    .NoArgsConstructor
    0.07
    >"
    ↵
    0.06
     _:
    0.06
     kov
    0.06
     Infos
    0.06
     McCoy
    0.06
     rus
    0.06
    _subplot
    0.06
    .GetMapping
    0.06
     NSS
    0.06
    Activations Density 0.400%

    No Known Activations