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. 118706
    Prev
    Next
    INDEX
    Explanations

    references to academic journals and publications in scientific contexts

    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
    itele
    -0.09
    podob
    -0.08
    AndGet
    -0.08
    obre
    -0.08
    ummings
    -0.07
    pte
    -0.07
    isque
    -0.07
    СÐŀ
    -0.07
     ëĦ¤ìĿ´íĬ¸
    -0.07
    аÑĢам
    -0.07
    POSITIVE LOGITS
    /Foundation
    0.06
    RS
    0.06
    82
    0.06
    ¸
    0.06
    198
    0.06
    59
    0.05
    54
    0.05
    119
    0.05
    ager
    0.05
    92
    0.05
    Activations Density 0.026%

    No Known Activations