© 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. 15-LLAMASCOPE-RES-131K
    11. 922
    Prev
    Next
    INDEX
    Explanations

    phrases related to the availability of information or resources

    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
     right
    -0.06
     Campbell
    -0.06
     Lear
    -0.06
    _MPI
    -0.06
    LEAR
    -0.06
    hab
    -0.06
    ëħ
    -0.05
    835
    -0.05
     post
    -0.05
     Writes
    -0.05
    POSITIVE LOGITS
    obre
    0.08
     seedu
    0.07
     tou
    0.07
     eldre
    0.07
    seau
    0.06
    wish
    0.06
    andex
    0.06
     Historic
    0.06
     IDisposable
    0.06
     historic
    0.06
    Activations Density 0.000%

    No Known Activations