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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93935
    Prev
    Next
    INDEX
    Explanations

    references to financial performance and reporting timeframes

    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
    æ¦
    -0.08
    ãĥªãĤ«
    -0.08
    ActionCreators
    -0.07
    nap
    -0.07
    ILLE
    -0.07
    _resolver
    -0.07
    oop
    -0.07
    beiter
    -0.07
    ëł
    -0.07
    MMdd
    -0.07
    POSITIVE LOGITS
     period
    0.07
     periods
    0.07
    is
    0.06
    annis
    0.06
    erald
    0.06
    fak
    0.06
    lin
    0.06
    È
    0.06
    es
    0.06
    period
    0.06
    Activations Density 0.005%

    No Known Activations