© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126333
    Prev
    Next
    INDEX
    Explanations

    references to regular or standard items or concepts

    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
       
    -0.07
     both
    -0.06
    ids
    -0.06
     twin
    -0.06
     able
    -0.06
     via
    -0.06
     somewhere
    -0.06
    ile
    -0.06
     tam
    -0.06
    aln
    -0.05
    POSITIVE LOGITS
     ordinary
    0.13
    ordinary
    0.11
    æĻ®éĢļ
    0.10
     æĻ®éĢļ
    0.10
    /plain
    0.10
    /simple
    0.09
    weg
    0.09
     normal
    0.09
    NORMAL
    0.09
    (non
    0.09
    Activations Density 0.021%

    No Known Activations