© 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. 10-LLAMASCOPE-RES-32K
    11. 29878
    Prev
    Next
    INDEX
    Explanations

    references to body parts and physical injuries or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toe
    -0.15
    ãĤ¹ãĥĨãĤ£
    -0.15
    elem
    -0.14
    .EventHandler
    -0.14
    haf
    -0.14
     Seal
    -0.14
    zw
    -0.14
    åªĴ
    -0.14
    _WARNINGS
    -0.13
     Toe
    -0.13
    POSITIVE LOGITS
    /body
    0.20
    /head
    0.18
    glomer
    0.17
    /arm
    0.15
    neys
    0.15
    wind
    0.15
    /back
    0.14
    éĻħ
    0.14
    ume
    0.14
     IHttp
    0.14
    Activations Density 0.075%

    No Known Activations