© 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. 125962
    Prev
    Next
    INDEX
    Explanations

    references to sizes or measurements

    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
    aim
    -0.06
    ideographic
    -0.06
    cell
    -0.06
    arium
    -0.06
    china
    -0.06
    æijĺè¦ģ
    -0.05
     outstanding
    -0.05
    perm
    -0.05
     guten
    -0.05
    orra
    -0.05
    POSITIVE LOGITS
    åģ¶
    0.08
    ude
    0.08
    berman
    0.07
    Äįi
    0.07
    ê¸Ī
    0.07
    ussen
    0.07
     Äijây
    0.07
    uzu
    0.07
    374
    0.07
    ájem
    0.07
    Activations Density 0.001%

    No Known Activations