© 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. 55800
    Prev
    Next
    INDEX
    Explanations

    terms related to return policies and restrictions

    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
     Ago
    -0.06
    743
    -0.06
    еÑī
    -0.06
    iac
    -0.06
    неÑģÑĤи
    -0.06
    ãĥ©ãĥ³ãĥī
    -0.05
    rand
    -0.05
     Pruitt
    -0.05
    pires
    -0.05
    æ§ĭ
    -0.05
    POSITIVE LOGITS
     nor
    0.08
     unless
    0.07
     NOR
    0.07
    ammed
    0.07
    unless
    0.06
    _Final
    0.06
    orsk
    0.06
    ipa
    0.06
    -vars
    0.06
    td
    0.06
    Activations Density 0.003%

    No Known Activations