© 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. 126003
    Prev
    Next
    INDEX
    Explanations

    references to mental health struggles and self-criticism

    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
    andle
    -0.07
     forcibly
    -0.06
    bond
    -0.06
     Huffman
    -0.06
    lad
    -0.06
    Bond
    -0.06
    icas
    -0.06
    Ãı
    -0.06
     na
    -0.06
     forced
    -0.06
    POSITIVE LOGITS
    -self
    0.08
     внÑĥ
    0.07
     self
    0.07
    æ®Ĭ
    0.07
     escorte
    0.07
    /self
    0.07
     Decompiled
    0.07
     pep
    0.06
    Ī¬
    0.06
    BEL
    0.06
    Activations Density 0.010%

    No Known Activations