© 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. 84577
    Prev
    Next
    INDEX
    Explanations

    phrases related to view counts and recent activity

    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
    ansom
    -0.07
    олиÑĤ
    -0.07
    ovel
    -0.06
    eyed
    -0.06
    rored
    -0.06
     Brady
    -0.06
    reed
    -0.06
     bufsize
    -0.06
    nal
    -0.06
    Ñīей
    -0.06
    POSITIVE LOGITS
    áºł
    0.08
     Wag
    0.06
    holm
    0.06
     Sho
    0.06
    allback
    0.06
     æIJ
    0.06
    _REGS
    0.06
    oggler
    0.06
    _customize
    0.06
     Bah
    0.06
    Activations Density 0.002%

    No Known Activations