© 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. 74872
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating relationships or actions involving people or objects

    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
    ainter
    -0.07
    ester
    -0.07
    que
    -0.07
    ÙĪØ±ÙĬ
    -0.07
     onto
    -0.07
    com
    -0.07
    ufen
    -0.07
    маз
    -0.07
    QUIRE
    -0.07
    esel
    -0.07
    POSITIVE LOGITS
     nhau
    0.10
    -about
    0.07
    ABCDEFGHIJKLMNOP
    0.07
    oj
    0.07
    _about
    0.07
     about
    0.07
    afort
    0.07
     Lod
    0.07
    üh
    0.06
    uhn
    0.06
    Activations Density 0.014%

    No Known Activations