© 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. 5-LLAMASCOPE-RES-131K
    11. 126388
    Prev
    Next
    INDEX
    Explanations

    measurements in centimeters

    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
    uby
    -0.07
    atch
    -0.07
    uh
    -0.07
     conventional
    -0.07
     PMID
    -0.06
    oub
    -0.06
     à¤ĩसस
    -0.06
    باÙĨ
    -0.06
    erd
    -0.06
    Ïħγ
    -0.06
    POSITIVE LOGITS
    èĥ¶
    0.08
    reon
    0.07
    eters
    0.07
    endoza
    0.06
    achines
    0.06
     Ler
    0.06
    krát
    0.06
    ãĤŀ
    0.06
    soft
    0.06
    idia
    0.06
    Activations Density 0.016%

    No Known Activations