© 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. 25-LLAMASCOPE-RES-32K
    6. 19136
    Prev
    Next
    INDEX
    Explanations

    occurrences of struct and interface keywords in programming code

    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
    acco
    -0.20
    optic
    -0.15
     Mits
    -0.15
    ãģĮãģĬ
    -0.14
     spoj
    -0.14
    ÙĪØ´
    -0.14
    hei
    -0.14
    aku
    -0.14
     Agricult
    -0.14
    verture
    -0.14
    POSITIVE LOGITS
     {↵
    0.19
     Damon
    0.17
    {}
    0.17
    {},
    0.16
    ible
    0.15
    {}↵↵
    0.15
     pumped
    0.14
     casualty
    0.14
    nas
    0.14
    uitka
    0.14
    Activations Density 0.002%

    No Known Activations