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. 71200
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    edo
    -0.06
    ÑģоÑĢ
    -0.06
     Pandora
    -0.06
     Fra
    -0.06
    ëĿ¼ëıĦ
    -0.06
     Burke
    -0.05
    ivy
    -0.05
    ид
    -0.05
    DED
    -0.05
    nds
    -0.05
    POSITIVE LOGITS
    ÑĥлÑİ
    0.08
    aset
    0.07
    postalcode
    0.07
    oyal
    0.07
    adesh
    0.07
    ãģĭãģĹ
    0.06
    é¡į
    0.06
    PFN
    0.06
    esinden
    0.06
    byn
    0.06
    Activations Density 0.000%

    No Known Activations