© 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. 9-LLAMASCOPE-RES-131K
    11. 95686
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" in various contexts

    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
    unning
    -0.07
    celik
    -0.07
    /root
    -0.06
    oS
    -0.06
    unct
    -0.06
    inos
    -0.06
    levant
    -0.06
    pios
    -0.06
    ört
    -0.06
    letic
    -0.06
    POSITIVE LOGITS
    pun
    0.07
    Äįet
    0.07
    ÑģÑİ
    0.06
     zda
    0.06
     Instruments
    0.06
    ://%
    0.06
    åĵ
    0.06
    adal
    0.06
    lah
    0.06
    _nullable
    0.06
    Activations Density 0.028%

    No Known Activations