© 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. 30833
    Prev
    Next
    INDEX
    Explanations

    references to participants or entities involved in various processes and requirements

    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
    agram
    -0.15
    forman
    -0.14
    UBY
    -0.14
    _iff
    -0.14
     wasn
    -0.13
    ानन
    -0.13
    رÙģØ©
    -0.13
    르ê²Į
    -0.13
    Ù¬
    -0.13
    ëŀľëĵľ
    -0.13
    POSITIVE LOGITS
     must
    0.38
     may
    0.36
     MUST
    0.33
     shall
    0.33
     wishing
    0.31
     can
    0.28
    must
    0.27
     MAY
    0.27
     mush
    0.26
     SHALL
    0.25
    Activations Density 0.101%

    No Known Activations