© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95638
    Prev
    Next
    INDEX
    Explanations

    concepts related to purpose and mission statements

    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
     inform
    -0.07
    ilon
    -0.07
     cooled
    -0.07
    stroy
    -0.07
    XI
    -0.06
    iguous
    -0.06
    odu
    -0.06
    quette
    -0.06
     marks
    -0.06
    Ñıк
    -0.06
    POSITIVE LOGITS
     Sacred
    0.07
    ullet
    0.06
    ÏĢη
    0.06
    ogh
    0.06
    por
    0.06
     defaultMessage
    0.06
    eker
    0.06
    çĻĤ
    0.06
     Darling
    0.06
     اÙĦعاÙĦÙħÙĬØ©
    0.06
    Activations Density 0.014%

    No Known Activations