© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 4365
    Prev
    Next
    INDEX
    Explanations

    references to album titles or track listings

    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
    _usec
    -0.07
    erson
    -0.06
    ibbon
    -0.06
    osite
    -0.06
     Musical
    -0.06
     ref
    -0.06
    éĢ¸
    -0.05
    در
    -0.05
     Mig
    -0.05
     angle
    -0.05
    POSITIVE LOGITS
     ìķĬìĿĦ
    0.07
    itzer
    0.07
    fon
    0.06
    ¦æĥħ
    0.06
    SRC
    0.06
     backing
    0.06
    bonus
    0.06
    plers
    0.06
    ahlen
    0.06
    /umd
    0.06
    Activations Density 0.002%

    No Known Activations