© 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. 17-LLAMASCOPE-RES-131K
    11. 94160
    Prev
    Next
    INDEX
    Explanations

    the phrase "The" at the beginning of sentences or paragraphs

    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
    .pixel
    -0.07
    usions
    -0.06
    ignKey
    -0.06
     dostan
    -0.06
     Woodward
    -0.06
    lah
    -0.06
    è©
    -0.06
    entimes
    -0.06
    inger
    -0.06
    poÄį
    -0.06
    POSITIVE LOGITS
    urum
    0.07
    ssf
    0.07
    imi
    0.07
    ooke
    0.07
    amac
    0.07
     Certif
    0.07
    peq
    0.06
    hle
    0.06
     Lair
    0.06
    çĵ
    0.06
    Activations Density 0.075%

    No Known Activations