© 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. 30-LLAMASCOPE-RES-32K
    11. 11450
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to functions and operations in abstract settings

    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
    (x
    -0.41
     x
    -0.39
    [x
    -0.38
    ,x
    -0.38
    /x
    -0.37
    =x
    -0.36
    |x
    -0.35
     xv
    -0.34
     xx
    -0.32
    $x
    -0.32
    POSITIVE LOGITS
     X
    0.82
    X
    0.66
    	X
    0.53
    *X
    0.51
    _X
    0.51
    >X
    0.49
    .X
    0.49
    -X
    0.48
    =X
    0.47
    (X
    0.47
    Activations Density 0.135%

    No Known Activations