© 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. 27-LLAMASCOPE-RES-32K
    11. 2813
    Prev
    Next
    INDEX
    Explanations

    interactions within a discussion or response thread

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apers
    -0.16
    athi
    -0.14
    ought
    -0.14
     пиÑģÑĮ
    -0.14
    è«ĸ
    -0.14
    inya
    -0.14
     candid
    -0.14
    parer
    -0.14
     è«
    -0.14
    eti
    -0.13
    POSITIVE LOGITS
     OP
    0.33
     bounty
    0.32
     Stack
    0.29
    OP
    0.26
     voted
    0.23
    .stack
    0.23
     stack
    0.23
    (OP
    0.23
     answer
    0.22
     posted
    0.22
    Activations Density 0.080%

    No Known Activations