Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 8-LLAMASCOPE-RES-32K
    6. 22728
    Prev
    Next
    INDEX
    Explanations

    occurrences of function definitions and related programming structures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rana
    -0.18
    andle
    -0.16
    ovah
    -0.15
    GuidId
    -0.15
    iales
    -0.14
     âĹij
    -0.14
    RuleContext
    -0.14
    rosso
    -0.14
    fade
    -0.14
    IALIZ
    -0.14
    POSITIVE LOGITS
    (
    0.15
     shaken
    0.14
    _
    0.14
     Blaze
    0.14
    ury
    0.14
    :
    0.14
     bi
    0.14
    bi
    0.14
    str
    0.14
     Hart
    0.13
    Activations Density 0.016%

    No Known Activations