© 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. 15-LLAMASCOPE-RES-131K
    11. 61922
    Prev
    Next
    INDEX
    Explanations

    terms related to aspirations and emotional experiences in creative fields

    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
    cznie
    -0.08
    å¾³
    -0.07
    _EMIT
    -0.07
    rotch
    -0.07
    iliz
    -0.07
    ozy
    -0.07
    Brains
    -0.06
    nite
    -0.06
    ounder
    -0.06
    å¿į
    -0.06
    POSITIVE LOGITS
    istes
    0.06
     playbook
    0.06
    455
    0.06
    ofs
    0.06
    fid
    0.06
     multiples
    0.06
    /storage
    0.06
     dr
    0.06
     veteran
    0.05
     bre
    0.05
    Activations Density 0.048%

    No Known Activations