© 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. 30-LLAMASCOPE-RES-32K
    6. 19791
    Prev
    Next
    INDEX
    Explanations

    ellipses or breaks in text, indicating pauses or omitted information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iolet
    -0.15
    itemap
    -0.15
    ãĥĨãĥ«
    -0.15
     reversible
    -0.15
    lay
    -0.14
    ìļ©
    -0.14
     Shields
    -0.14
    naissance
    -0.13
     ↵↵
    -0.13
     základ
    -0.13
    POSITIVE LOGITS
    !--
    0.15
    tember
    0.15
     Leer
    0.15
     Leia
    0.14
     read
    0.14
    asan
    0.14
     <|
    0.14
     dive
    0.14
     à¤ħध
    0.14
    ÑĦеÑĢ
    0.14
    Activations Density 0.023%

    No Known Activations