© 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. 75128
    Prev
    Next
    INDEX
    Explanations

    negative qualifiers and remarks about expectations or assumptions

    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
     ANY
    -0.07
    rix
    -0.06
    ä»»ä½ķ
    -0.06
     atleast
    -0.06
    AWN
    -0.06
    ayi
    -0.06
    RIX
    -0.06
     NEVER
    -0.06
    opes
    -0.06
     quoi
    -0.06
    POSITIVE LOGITS
     immediate
    0.10
     strictly
    0.10
     necessarily
    0.10
     exact
    0.10
     direct
    0.10
     strict
    0.10
     certain
    0.10
     directly
    0.09
     full
    0.09
     immedi
    0.09
    Activations Density 0.091%

    No Known Activations