© 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. 17-LLAMASCOPE-RES-32K
    11. 12839
    Prev
    Next
    INDEX
    Explanations

    phrases and metrics related to market share and comparisons among brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onders
    -0.13
    jon
    -0.13
    ÑĢел
    -0.13
    биÑĤ
    -0.13
     blat
    -0.13
    ultimate
    -0.13
    åĪº
    -0.13
    ult
    -0.12
     fours
    -0.12
    еÑģÑı
    -0.12
    POSITIVE LOGITS
     next
    0.40
    next
    0.36
     Next
    0.33
    Next
    0.32
     second
    0.32
    _next
    0.31
    次
    0.30
    -next
    0.29
     NEXT
    0.29
    (next
    0.29
    Activations Density 0.094%

    No Known Activations