© 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. 77321
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" and related phrases that indicate presence or involvement

    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
    atch
    -0.07
    ehr
    -0.06
    endra
    -0.06
    peng
    -0.06
    ika
    -0.06
    OSP
    -0.06
    ायà¤ķ
    -0.05
    rish
    -0.05
     æĢ
    -0.05
    ÑĥлÑı
    -0.05
    POSITIVE LOGITS
     ÑĩÑĤобÑĭ
    0.13
     Äijá»ĥ
    0.12
     attempt
    0.11
     inorder
    0.11
    attempt
    0.10
     afin
    0.10
     Ñīоб
    0.10
     to
    0.10
     nhằm
    0.10
    Attempt
    0.09
    Activations Density 0.039%

    No Known Activations