© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 8-LLAMASCOPE-RES-32K
    6. 5298
    Prev
    Next
    INDEX
    Explanations

    references to accessibility and compatibility across various devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anas
    -0.18
    obl
    -0.16
    icana
    -0.16
    лÑĥÑĪ
    -0.15
     Alo
    -0.14
    олиÑĤ
    -0.14
    .nlm
    -0.14
     Harness
    -0.14
    xies
    -0.14
    hcp
    -0.14
    POSITIVE LOGITS
    _REGISTRY
    0.15
    ạn
    0.14
    haf
    0.14
    dev
    0.13
    amon
    0.13
    skill
    0.13
    /table
    0.13
    lam
    0.13
    -os
    0.13
    over
    0.13
    Activations Density 0.045%

    No Known Activations