Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43925
    Prev
    Next
    INDEX
    Explanations

    terms related to neuroscience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fak
    -0.08
    ngth
    -0.08
     Birch
    -0.07
    isia
    -0.07
    niž
    -0.07
    oltip
    -0.07
    alaria
    -0.07
    è³¢
    -0.07
    YTE
    -0.07
    dzi
    -0.07
    POSITIVE LOGITS
    ropsych
    0.20
    rom
    0.17
    rol
    0.14
    rops
    0.13
    ops
    0.10
    ropa
    0.10
    ropol
    0.10
    ROM
    0.10
    rop
    0.10
    roman
    0.10
    Activations Density 0.002%

    No Known Activations