© 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. 106354
    Prev
    Next
    INDEX
    Explanations

    the concept of clarity and transparency in communication or situations

    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
    дин
    -0.07
    ok
    -0.07
    iro
    -0.06
    ampo
    -0.06
    rey
    -0.06
    ez
    -0.06
    vez
    -0.06
    omm
    -0.06
    dl
    -0.06
    kar
    -0.06
    POSITIVE LOGITS
     дека
    0.08
     mastur
    0.08
    apixel
    0.07
    ãĥŁãĥ¥
    0.07
    ä¸ĢçĤ¹
    0.07
    oload
    0.07
    опаÑģ
    0.07
    mente
    0.07
     bahwa
    0.07
    ahir
    0.07
    Activations Density 0.005%

    No Known Activations