© 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. 70873
    Prev
    Next
    INDEX
    Explanations

    significant nouns and phrases related to collections and trends

    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
    untas
    -0.06
    наÑĢ
    -0.06
    enser
    -0.05
     Isis
    -0.05
     Hass
    -0.05
    adle
    -0.05
    862
    -0.05
    mlink
    -0.05
     cust
    -0.05
    erial
    -0.05
    POSITIVE LOGITS
     discrepan
    0.08
    åĵ
    0.08
    ÑĮÑİÑĤ
    0.08
    ippers
    0.07
    inus
    0.07
    _fh
    0.07
    ernaut
    0.07
     Abed
    0.07
    arend
    0.06
    neau
    0.06
    Activations Density 0.004%

    No Known Activations