© 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. 15-LLAMASCOPE-RES-131K
    6. 26803
    Prev
    Next
    INDEX
    Explanations

    specific actions or commands related to software operations

    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
     frost
    -0.06
    amp
    -0.06
    regnum
    -0.06
    dh
    -0.06
    amo
    -0.06
     Frost
    -0.06
    osten
    -0.06
    íĤ¹
    -0.06
     Fro
    -0.06
    azar
    -0.06
    POSITIVE LOGITS
    ĶåĽŀ
    0.08
    iger
    0.07
    udo
    0.07
    ayne
    0.06
    bsite
    0.06
    Destructor
    0.06
    SITE
    0.06
    rahim
    0.06
    ENDIF
    0.06
     onHide
    0.06
    Activations Density 0.005%

    No Known Activations