© 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. 2917
    Prev
    Next
    INDEX
    Explanations

    concepts associated with evaluation and analysis of financial conditions or performance

    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
    /ag
    -0.28
    /al
    -0.24
    /ar
    -0.22
    /ad
    -0.21
    /App
    -0.20
    /ap
    -0.20
    /an
    -0.19
    /arch
    -0.19
    @app
    -0.19
     Appet
    -0.19
    POSITIVE LOGITS
    ãĤ¢
    0.49
     ãĤ¢
    0.40
    -A
    0.38
    _A
    0.37
    ãĥ»ãĤ¢
    0.35
    á
    0.34
    ÐIJ
    0.32
    Äģ
    0.30
     ÐIJ
    0.29
     ìķĦ
    0.28
    Activations Density 0.369%

    No Known Activations