© 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. 84652
    Prev
    Next
    INDEX
    Explanations

    the word "by" used in various contexts related to actions or methods

    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
    EFR
    -0.09
    awning
    -0.08
    RAP
    -0.08
    iyan
    -0.07
    resher
    -0.07
    mÃŃt
    -0.07
    otts
    -0.07
    ificador
    -0.07
    openh
    -0.07
    .scal
    -0.07
    POSITIVE LOGITS
     simply
    0.09
     use
    0.09
     using
    0.08
     direct
    0.07
     means
    0.07
     taking
    0.07
     sum
    0.07
     simple
    0.06
    260
    0.06
    oda
    0.06
    Activations Density 0.055%

    No Known Activations