© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 70920
    Prev
    Next
    INDEX
    Explanations

    negative phrases regarding availability and accessibility issues

    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
    asis
    -0.06
     instead
    -0.06
    èĬ±
    -0.06
    \Backend
    -0.06
    .defaults
    -0.06
    .ssl
    -0.06
    деÑĢ
    -0.06
    siz
    -0.05
    udic
    -0.05
     thr
    -0.05
    POSITIVE LOGITS
    SHOT
    0.08
     anymore
    0.08
    astreet
    0.07
    iger
    0.07
    idian
    0.06
    219
    0.06
    iyah
    0.06
    icho
    0.06
    \<^
    0.06
    足
    0.06
    Activations Density 0.026%

    No Known Activations