© 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. 56366
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "In," particularly at the beginning of sentences

    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
    eries
    -0.08
    .ravel
    -0.07
    edef
    -0.07
    heim
    -0.06
    ãĤ¢ãĥ¼
    -0.06
    uces
    -0.06
    ery
    -0.06
    å½Ĵ
    -0.06
    viders
    -0.06
    loads
    -0.06
    POSITIVE LOGITS
     an
    0.07
    amin
    0.06
     Dup
    0.06
    osu
    0.06
    rama
    0.06
     a
    0.06
     iv
    0.06
    overn
    0.06
     today
    0.06
    /sdk
    0.06
    Activations Density 0.018%

    No Known Activations