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. 29-LLAMASCOPE-RES-32K
    6. 4446
    Prev
    Next
    INDEX
    Explanations

    content related to Canadian television programming and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "(\<
    -0.15
    resa
    -0.14
    amment
    -0.14
    ãĥ©ãĤ¹
    -0.14
    ledger
    -0.14
    uali
    -0.14
    ibre
    -0.14
    ofs
    -0.14
     LAP
    -0.14
    ebi
    -0.14
    POSITIVE LOGITS
     Rogers
    0.23
     Gemini
    0.20
    rab
    0.19
     CBC
    0.18
     Shaw
    0.18
     Bell
    0.18
     Much
    0.17
    .ct
    0.17
    _CBC
    0.16
     TIFF
    0.16
    Activations Density 0.043%

    No Known Activations