© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 23-LLAMASCOPE-RES-32K
    11. 30877
    Prev
    Next
    INDEX
    Explanations

    references to specific films, artists, and notable figures in the entertainment industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LastError
    -0.15
    PACE
    -0.15
    .quality
    -0.14
    Ø®ÙĪ
    -0.14
    uye
    -0.14
    ROUTE
    -0.14
     suyu
    -0.13
    ROUT
    -0.13
     Podesta
    -0.13
    vars
    -0.13
    POSITIVE LOGITS
    elight
    0.17
    entious
    0.16
    sembler
    0.15
    orious
    0.15
    ä¸ĸ
    0.14
     targ
    0.14
    imate
    0.14
    álo
    0.14
    unny
    0.14
    gies
    0.13
    Activations Density 0.332%

    No Known Activations