© 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. 17-LLAMASCOPE-RES-131K
    11. 125318
    Prev
    Next
    INDEX
    Explanations

    references to collective experiences and social dynamics

    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
    æĽ°
    -0.07
    zcze
    -0.07
    моÑĤ
    -0.07
    .OrderByDescending
    -0.07
    angkan
    -0.06
    OMIC
    -0.06
    forder
    -0.06
    ÑĤаж
    -0.06
     æ¶
    -0.06
     Yan
    -0.06
    POSITIVE LOGITS
    782
    0.07
     might
    0.06
    418
    0.06
    ober
    0.06
    ark
    0.06
    pez
    0.06
    pires
    0.06
    appendChild
    0.06
    vertis
    0.06
    Į
    0.06
    Activations Density 0.057%

    No Known Activations