© 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. 29-LLAMASCOPE-RES-32K
    11. 17102
    Prev
    Next
    INDEX
    Explanations

    numerical representations of parameters and variables related to flow dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¢ĥ
    -0.14
     `
    -0.14
     Lamb
    -0.14
     Laguna
    -0.13
    [`
    -0.13
     Prec
    -0.13
     Gray
    -0.13
     Dob
    -0.13
    но
    -0.13
     gray
    -0.13
    POSITIVE LOGITS
    $
    0.46
    $,
    0.42
    $.
    0.40
    $↵
    0.39
    }$
    0.39
    $",
    0.38
    )$
    0.38
    '$
    0.37
    $"
    0.36
    ?$
    0.34
    Activations Density 0.395%

    No Known Activations