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. 27-LLAMASCOPE-RES-32K
    6. 11840
    Prev
    Next
    INDEX
    Explanations

    references to the Twitch platform and its related content

    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
    ordova
    -0.19
    odesk
    -0.15
     phóng
    -0.15
    au
    -0.15
     nodeName
    -0.14
     Zuk
    -0.14
    ostel
    -0.14
    /preferences
    -0.14
    odom
    -0.14
    aron
    -0.14
    POSITIVE LOGITS
     stream
    0.44
     Stream
    0.37
     streams
    0.36
     Twitch
    0.36
    -stream
    0.34
    (stream
    0.32
    .stream
    0.32
     twitch
    0.32
    stream
    0.32
    Stream
    0.32
    Activations Density 0.017%

    No Known Activations