© 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. 125334
    Prev
    Next
    INDEX
    Explanations

    expressions of interpersonal relationships and emotional connections

    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
    awah
    -0.08
    asu
    -0.08
    ifax
    -0.08
    áp
    -0.08
    izu
    -0.08
    uib
    -0.08
    lerimiz
    -0.08
    ımıza
    -0.08
    awi
    -0.07
    allo
    -0.07
    POSITIVE LOGITS
     had
    0.07
    岡
    0.07
    iš
    0.06
     Lear
    0.06
     himself
    0.06
     concert
    0.05
     t
    0.05
     now
    0.05
     tact
    0.05
     can
    0.05
    Activations Density 0.005%

    No Known Activations