© 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. 15-LLAMASCOPE-RES-131K
    6. 1034
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "with" 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
    HEET
    -0.06
    amı
    -0.06
    uai
    -0.06
    uro
    -0.06
    owitz
    -0.06
    èĩªæ²»
    -0.06
    aukee
    -0.06
     Harbor
    -0.06
    ediator
    -0.05
    ámara
    -0.05
    POSITIVE LOGITS
     Thanh
    0.07
    IFS
    0.06
    éļł
    0.06
    than
    0.06
    NameValuePair
    0.06
    aliz
    0.06
    翼
    0.06
    ettel
    0.06
     Frank
    0.06
    PCS
    0.06
    Activations Density 0.020%

    No Known Activations