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. 78449
    Prev
    Next
    INDEX
    Explanations

    punctuation and connecting phrases that indicate association or transition in text

    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
    doi
    -0.06
     tall
    -0.06
    ivar
    -0.05
    âŁ
    -0.05
     Mo
    -0.05
     mild
    -0.05
     tet
    -0.05
    pg
    -0.05
     Combat
    -0.05
    etto
    -0.05
    POSITIVE LOGITS
     Roe
    0.09
    _IMPORTED
    0.09
    ĨĴ
    0.08
    å·Ŀ
    0.08
    conj
    0.08
    /***/
    0.07
    .Elements
    0.07
    alink
    0.07
    idth
    0.07
    ajs
    0.07
    Activations Density 0.005%

    No Known Activations