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. 1849
    Prev
    Next
    INDEX
    Explanations

    references to software and technical tools

    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
    ãĢĩ
    -0.16
    má
    -0.14
     Airbnb
    -0.14
     trav
    -0.14
     Vict
    -0.14
    elix
    -0.13
     scrim
    -0.13
     HACK
    -0.13
    glich
    -0.13
     Fac
    -0.13
    POSITIVE LOGITS
     batch
    0.18
     Professional
    0.18
     fre
    0.18
    skins
    0.18
    Trial
    0.18
    .batch
    0.18
    _batch
    0.17
     professional
    0.17
    .Registry
    0.17
     DevComponents
    0.17
    Activations Density 0.104%

    No Known Activations