© 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. 26-LLAMASCOPE-RES-32K
    11. 6989
    Prev
    Next
    INDEX
    Explanations

    terms related to sports rankings and tournament progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erli
    -0.16
    ůst
    -0.15
    usan
    -0.15
    .codes
    -0.14
    ilst
    -0.13
    .snap
    -0.13
    ograd
    -0.13
    industry
    -0.13
    plit
    -0.13
    ļ
    -0.13
    POSITIVE LOGITS
     seed
    0.48
     seeds
    0.43
    seed
    0.43
     Seed
    0.40
    Seed
    0.37
     Seeds
    0.36
     seeded
    0.34
    .seed
    0.34
    _seed
    0.34
    -se
    0.33
    Activations Density 0.027%

    No Known Activations