© 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. 17-LLAMASCOPE-RES-131K
    6. 83046
    Prev
    Next
    INDEX
    Explanations

    terms related to "cryogenic" processes or features

    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
    Wunused
    -0.08
    icare
    -0.07
    quate
    -0.06
    otate
    -0.06
    fü
    -0.06
    EMENT
    -0.06
    ivalent
    -0.06
    VILLE
    -0.06
    iae
    -0.06
    solete
    -0.06
    POSITIVE LOGITS
    tek
    0.09
    er
    0.09
    ogenic
    0.08
    pper
    0.07
    echn
    0.07
    nda
    0.07
    jedn
    0.07
    cek
    0.07
    rey
    0.06
    vor
    0.06
    Activations Density 0.003%

    No Known Activations