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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95979
    Prev
    Next
    INDEX
    Explanations

    numerical references and citations in academic writing

    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
    htags
    -0.07
    erez
    -0.07
     summons
    -0.06
    urdu
    -0.06
    оÑı
    -0.06
     NavParams
    -0.06
    ewear
    -0.05
    -Day
    -0.05
    _BOTH
    -0.05
    isoner
    -0.05
    POSITIVE LOGITS
    unner
    0.08
    NAMESPACE
    0.07
    InBackground
    0.07
    aco
    0.07
    ì§ľ
    0.06
    ãģ¾ãģļ
    0.06
    conds
    0.06
    146
    0.06
    quo
    0.06
    Gratis
    0.06
    Activations Density 0.007%

    No Known Activations