Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 106167
    Prev
    Next
    INDEX
    Explanations

    comments or annotations within a technical or academic context

    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
    coe
    -0.07
    airo
    -0.07
    rimp
    -0.07
    clerosis
    -0.07
    asan
    -0.07
    ingo
    -0.07
    ümü
    -0.06
    Ñıн
    -0.06
    abled
    -0.06
    éĻ£
    -0.06
    POSITIVE LOGITS
     Mandal
    0.06
    manda
    0.06
    Notifier
    0.06
    094
    0.06
    _AI
    0.06
    hua
    0.05
    enticator
    0.05
    tach
    0.05
     gross
    0.05
     pap
    0.05
    Activations Density 0.010%

    No Known Activations