© 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. 31-LLAMASCOPE-RES-32K
    11. 10967
    Prev
    Next
    INDEX
    Explanations

    questions and serious discussions revolving around personal experiences and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [...
    -0.20
     [âĢ¦]↵
    -0.20
     [...]
    -0.19
     [âĢ¦]...↵
    -0.19
     [âĢ¦]
    -0.18
     enthusi
    -0.17
     [...]↵↵
    -0.17
     [âĢ¦]↵↵
    -0.16
     ...↵
    -0.15
    actionDate
    -0.15
    POSITIVE LOGITS
    udu
    0.12
    sut
    0.12
    hangi
    0.12
    uzzy
    0.11
    achte
    0.11
    avra
    0.11
    celik
    0.11
     vlas
    0.11
    separator
    0.10
     sperma
    0.10
    Activations Density 1.211%

    No Known Activations