© 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. 26-LLAMASCOPE-RES-32K
    6. 20972
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and component management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    452
    -0.17
    Pairs
    -0.15
     sped
    -0.14
    shint
    -0.14
    rowse
    -0.14
    -valu
    -0.14
    767
    -0.14
    ç¿Ĵ
    -0.13
    ubit
    -0.13
    pike
    -0.12
    POSITIVE LOGITS
     depth
    0.37
     children
    0.34
     child
    0.34
     Depth
    0.33
    Depth
    0.33
    depth
    0.33
    _depth
    0.33
     childs
    0.30
    .depth
    0.30
     leaf
    0.30
    Activations Density 0.566%

    No Known Activations