© 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. 16707
    Prev
    Next
    INDEX
    Explanations

    concepts related to guidance and direction

    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
    Via
    -0.07
    652
    -0.06
    avia
    -0.06
    orgen
    -0.06
    [
    -0.06
    553
    -0.06
    urt
    -0.06
     whose
    -0.06
    placement
    -0.06
    ;
    -0.06
    POSITIVE LOGITS
    egin
    0.07
     Nie
    0.07
    ActionCreators
    0.07
    ÑĦиÑĨи
    0.07
    ưa
    0.07
    اÛĮÙĩ
    0.07
    Dll
    0.06
    ekil
    0.06
    akin
    0.06
    fait
    0.06
    Activations Density 0.003%

    No Known Activations