© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 11-LLAMASCOPE-RES-32K
    6. 7478
    Prev
    Next
    INDEX
    Explanations

    terms related to muscle health and physical training

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zilla
    -0.16
    ï¸
    -0.15
    å¾ħ
    -0.14
    acific
    -0.14
    reater
    -0.14
    еÑģа
    -0.14
    ê
    -0.14
    ÃŁ
    -0.14
    elper
    -0.14
    herence
    -0.14
    POSITIVE LOGITS
    ic
    0.14
    uffs
    0.14
     Ranking
    0.14
     Amir
    0.13
    à¸Ļà¸Ħร
    0.13
    olls
    0.13
    -Ta
    0.13
     base
    0.13
     rehabilitation
    0.13
    /connect
    0.13
    Activations Density 0.028%

    No Known Activations