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. 17-LLAMASCOPE-RES-32K
    6. 26480
    Prev
    Next
    INDEX
    Explanations

    terms and references related to recorded media, specifically focusing on 'discs' and 'disk' throughout various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amas
    -0.17
     Tib
    -0.15
    ÙĪÙĦØ©
    -0.15
     ActiveForm
    -0.14
    ux
    -0.14
    chod
    -0.14
    chio
    -0.14
    YPES
    -0.14
     cin
    -0.14
    izer
    -0.14
    POSITIVE LOGITS
    arding
    0.21
    ografia
    0.20
    ursive
    0.19
    /disc
    0.19
    ette
    0.19
    ipline
    0.18
    -shaped
    0.17
    iplinary
    0.17
    Disc
    0.17
    regor
    0.16
    Activations Density 0.031%

    No Known Activations