© 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. 1929
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical and computational methods in scientific research

    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
    agnost
    -0.16
    ãĥ³ãĤ¿
    -0.16
     Kil
    -0.16
    ilst
    -0.15
    entic
    -0.15
    utenberg
    -0.15
    \Mapping
    -0.14
    agar
    -0.14
     decre
    -0.13
     convention
    -0.13
    POSITIVE LOGITS
     comb
    0.27
     knot
    0.23
     Lie
    0.21
     Rings
    0.19
     discrete
    0.19
     probability
    0.18
     Knot
    0.18
     dynam
    0.18
    Lie
    0.18
     topology
    0.17
    Activations Density 0.255%

    No Known Activations