© 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. 4595
    Prev
    Next
    INDEX
    Explanations

    references to specific "points" or perspectives within discussions

    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
    rana
    -0.18
    اÙģت
    -0.17
     Views
    -0.16
    /views
    -0.16
    opr
    -0.16
    rhs
    -0.16
     views
    -0.16
    views
    -0.16
    roit
    -0.15
    oola
    -0.15
    POSITIVE LOGITS
    -of
    0.22
    /cmd
    0.17
     Blank
    0.16
    sworth
    0.16
     blank
    0.15
    blank
    0.15
    ede
    0.15
    Blank
    0.15
    Vi
    0.15
    -counter
    0.15
    Activations Density 0.007%

    No Known Activations