© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 10830
    Prev
    Next
    INDEX
    Explanations

    references to people or groups in a community context

    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
     themselves
    -0.20
     and
    -0.17
     otherwise
    -0.17
     itself
    -0.16
    edly
    -0.16
    swers
    -0.15
    ibur
    -0.15
    rail
    -0.14
    åı¦ä¸Ģ
    -0.14
    isode
    -0.14
    POSITIVE LOGITS
    -than
    0.24
    wis
    0.20
    /new
    0.20
     besides
    0.20
    bes
    0.20
    world
    0.20
    most
    0.19
    /all
    0.17
    ness
    0.17
     türlü
    0.17
    Activations Density 0.046%

    No Known Activations