© 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. 40273
    Prev
    Next
    INDEX
    Explanations

    references to processes and procedures related to payments and accommodations

    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
    assel
    -0.07
    طاÙĦ
    -0.06
    eyen
    -0.06
    dap
    -0.06
    -Sah
    -0.06
    ackbar
    -0.06
    stry
    -0.06
    atasets
    -0.06
    anken
    -0.06
    eeper
    -0.06
    POSITIVE LOGITS
    oeff
    0.09
     is
    0.08
     are
    0.08
     please
    0.07
     will
    0.07
    sono
    0.07
    :↵
    0.07
    åŃIJãģ¯
    0.07
     HERE
    0.07
     actionTypes
    0.06
    Activations Density 0.023%

    No Known Activations