© 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. 56391
    Prev
    Next
    INDEX
    Explanations

    conditional phrases expressing expectations or outcomes

    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
    riad
    -0.07
     olacaktır
    -0.07
    üzel
    -0.07
    Ñĩие
    -0.07
    RequestId
    -0.07
    lien
    -0.07
     Extraction
    -0.07
    AFE
    -0.07
    ods
    -0.06
    acos
    -0.06
    POSITIVE LOGITS
     soon
    0.09
    soon
    0.08
     Soon
    0.07
    ingham
    0.07
    igan
    0.07
    Soon
    0.07
     Monter
    0.07
    ow
    0.07
     later
    0.07
    fully
    0.06
    Activations Density 0.087%

    No Known Activations