© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77376
    Prev
    Next
    INDEX
    Explanations

    terms related to mental health conditions and their biological factors

    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
    idis
    -0.07
    aug
    -0.07
    ç¤
    -0.07
     gebru
    -0.06
    arie
    -0.06
    afen
    -0.06
    ker
    -0.06
     Sense
    -0.06
    ecies
    -0.06
    bart
    -0.06
    POSITIVE LOGITS
    ãģ¶
    0.07
     allied
    0.06
    ogen
    0.06
    Äł
    0.06
    axe
    0.06
     Personality
    0.06
    ução
    0.06
     Brun
    0.06
     nos
    0.06
     brain
    0.06
    Activations Density 0.000%

    No Known Activations