© 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. 15-LLAMASCOPE-RES-131K
    11. 27649
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "in" and related context

    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
     traf
    -0.07
    formatted
    -0.06
    lander
    -0.06
    feld
    -0.06
    _compat
    -0.06
    iyi
    -0.06
     Proble
    -0.06
    å±Ĩ
    -0.06
    .§
    -0.06
    .Focused
    -0.06
    POSITIVE LOGITS
    anas
    0.07
    ahy
    0.07
    adera
    0.07
    ÑĢаз
    0.07
     stip
    0.07
    -Semit
    0.06
    elsen
    0.06
     whole
    0.06
    usz
    0.06
    anz
    0.06
    Activations Density 0.207%

    No Known Activations