© 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. 11015
    Prev
    Next
    INDEX
    Explanations

    identifiers and categories related to video game features and genres

    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
    Ø¡
    -0.16
    errat
    -0.14
    otech
    -0.14
     &
    -0.14
     Hardy
    -0.14
    ault
    -0.14
     https
    -0.14
     hack
    -0.14
    agner
    -0.13
     rock
    -0.13
    POSITIVE LOGITS
    bows
    0.15
    iglia
    0.14
     somew
    0.14
    -ÑĤаки
    0.13
     ÑģоÑģÑĤ
    0.13
     stÅĻ
    0.13
    алом
    0.13
    bugs
    0.13
     koneÄį
    0.13
    elay
    0.13
    Activations Density 0.021%

    No Known Activations