© 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. 5997
    Prev
    Next
    INDEX
    Explanations

    terms related to social media and digital marketing

    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
    ajas
    -0.17
     UCLA
    -0.16
    orns
    -0.15
     Georgia
    -0.15
    ritch
    -0.14
     FS
    -0.14
     Karn
    -0.14
     Frid
    -0.14
     UCS
    -0.14
    Georgia
    -0.13
    POSITIVE LOGITS
     Doyle
    0.39
     Newfoundland
    0.36
     Republic
    0.35
    Republic
    0.33
     Jake
    0.33
    Jake
    0.28
     republic
    0.26
     Irish
    0.26
     Donovan
    0.26
     RCMP
    0.26
    Activations Density 0.003%

    No Known Activations