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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 96053
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic association and historical 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
    591
    -0.07
    ahoo
    -0.06
    atura
    -0.06
     cellForRowAt
    -0.06
     Ha
    -0.06
    inning
    -0.06
    anim
    -0.06
    ibaba
    -0.06
    KeySpec
    -0.06
    906
    -0.06
    POSITIVE LOGITS
    ayi
    0.07
    à¥įà¤Łà¤®
    0.07
    ôt
    0.06
     ÙĪÙģ
    0.06
     ÑģоÑģÑĤоÑı
    0.06
     YaÅŁ
    0.06
    mamak
    0.06
    ÑıÑħ
    0.06
    öl
    0.06
    à¥Ĥ
    0.06
    Activations Density 0.014%

    No Known Activations