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. 4-LLAMASCOPE-RES-32K
    6. 30462
    Prev
    Next
    INDEX
    Explanations

    terms related to building and creating customized projects or gadgets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isko
    -0.17
    .Butter
    -0.15
    /Branch
    -0.15
    .byId
    -0.15
    LOCKS
    -0.15
    reten
    -0.14
    anela
    -0.14
    STYPE
    -0.14
    ifen
    -0.14
    YNC
    -0.14
    POSITIVE LOGITS
    acity
    0.17
    iola
    0.16
     Wolfe
    0.15
     Dod
    0.15
    ervas
    0.14
    ACITY
    0.14
    मर
    0.14
     swap
    0.14
     Daly
    0.14
    icine
    0.14
    Activations Density 0.265%

    No Known Activations