© 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. 25-LLAMASCOPE-RES-32K
    11. 10588
    Prev
    Next
    INDEX
    Explanations

    indicators of player performance and game statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assage
    -0.15
    ignon
    -0.14
    ãģŁãģı
    -0.14
     ÅĻ
    -0.14
    ache
    -0.14
    Insensitive
    -0.14
    /GPL
    -0.14
    robat
    -0.14
     inconvenient
    -0.14
     кв
    -0.13
    POSITIVE LOGITS
     giveaways
    0.19
     misc
    0.19
     struggles
    0.18
     struggle
    0.18
    çĬ¯
    0.17
     giveaway
    0.17
     tentative
    0.17
     costly
    0.16
     conced
    0.16
     committing
    0.16
    Activations Density 0.117%

    No Known Activations