© 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. 27-LLAMASCOPE-RES-32K
    11. 1491
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to contests, competitions, and prizes, particularly in the context of sports and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.13
    ':''
    -0.12
     &↵
    -0.12
    and
    -0.12
    ãģ°ãģĭãĤĬ
    -0.11
     to
    -0.11
     or
    -0.11
     but
    -0.10
     że
    -0.10
    ikon
    -0.10
    POSITIVE LOGITS
    ,
    0.43
    (),
    0.33
    !,
    0.31
    !!,
    0.30
    ा,
    0.30
    à¥ĩ,
    0.30
    à¥ĩà¤Ĥ,
    0.30
    à¹Į,
    0.29
    à¥ĭ,
    0.29
    *,
    0.29
    Activations Density 7.027%

    No Known Activations