© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 10370
    Prev
    Next
    INDEX
    Explanations

    references to speakers, researchers, and their affiliations in academic and professional contexts

    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
    klä
    -0.15
    à¸Ńà¸ļ
    -0.13
    ilio
    -0.13
    人åı£
    -0.12
    INCT
    -0.12
    Built
    -0.12
    locking
    -0.12
    celik
    -0.12
    овÑĸд
    -0.12
     uÄŁ
    -0.12
    POSITIVE LOGITS
     active
    0.30
     from
    0.30
     drawn
    0.30
     representing
    0.28
     involved
    0.26
     specializing
    0.26
     working
    0.26
     affiliated
    0.25
     specialized
    0.24
    from
    0.24
    Activations Density 0.140%

    No Known Activations