© 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. 87260
    Prev
    Next
    INDEX
    Explanations

    emotional connections and impactful themes in personal narratives

    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
    eview
    -0.07
    CompleteListener
    -0.07
    eturn
    -0.07
    ivor
    -0.07
    ané
    -0.07
    овиÑĩ
    -0.07
    áº
    -0.06
    ForResource
    -0.06
    ÎŃα
    -0.06
    outil
    -0.06
    POSITIVE LOGITS
     chords
    0.09
     chord
    0.08
     sensitive
    0.08
    hit
    0.08
     touch
    0.07
     nerve
    0.07
    _hit
    0.07
     buttons
    0.07
     raw
    0.07
     hit
    0.07
    Activations Density 0.045%

    No Known Activations