© 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. 40839
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating years

    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
    urb
    -0.08
    ermann
    -0.07
    umbo
    -0.07
    lacak
    -0.07
    hta
    -0.07
    lal
    -0.07
    oppel
    -0.07
    erman
    -0.07
    erv
    -0.07
    Solo
    -0.07
    POSITIVE LOGITS
    oped
    0.07
    lico
    0.07
    hed
    0.06
    HO
    0.06
    undance
    0.06
    iferay
    0.06
    716
    0.06
     pien
    0.06
    lesen
    0.06
    ỹ
    0.06
    Activations Density 0.006%

    No Known Activations