© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82358
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate presence or absence, especially in context of narration or dialogue

    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
    escal
    -0.08
    à¤ľà¤°
    -0.07
    crest
    -0.07
    ulen
    -0.07
    ripe
    -0.07
    asury
    -0.07
    resents
    -0.07
    eyse
    -0.07
    ãĥ£
    -0.07
    =-=-=-=-=-=-=-=-
    -0.06
    POSITIVE LOGITS
     Gia
    0.06
    offee
    0.06
     intake
    0.06
    Priv
    0.05
     Eins
    0.05
     artist
    0.05
     due
    0.05
    SD
    0.05
     artifact
    0.05
     Suff
    0.05
    Activations Density 0.004%

    No Known Activations