© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13318
    Prev
    Next
    INDEX
    Explanations

    references to missing or absent 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
    _IL
    -0.17
    .LoadScene
    -0.15
    _unref
    -0.15
    kol
    -0.14
    .useState
    -0.14
    mq
    -0.13
     unsustainable
    -0.13
    ůr
    -0.13
    å¹ķ
    -0.13
     ãĤŃãĥ£
    -0.13
    POSITIVE LOGITS
     missing
    0.85
    missing
    0.70
    Missing
    0.66
     Missing
    0.66
     MISSING
    0.64
     missed
    0.63
    miss
    0.60
     misses
    0.59
     miss
    0.58
    _missing
    0.57
    Activations Density 0.259%

    No Known Activations