© 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. 17-LLAMASCOPE-RES-131K
    11. 76152
    Prev
    Next
    INDEX
    Explanations

    terms related to input data and methodologies in research contexts

    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
    umu
    -0.06
     ifndef
    -0.06
    instanc
    -0.06
    ically
    -0.06
    roduced
    -0.06
    .wp
    -0.06
    hol
    -0.06
    PÅĻi
    -0.06
    948
    -0.06
    PRS
    -0.06
    POSITIVE LOGITS
    ystack
    0.07
    reamble
    0.07
    ources
    0.07
     overview
    0.07
    erequisites
    0.07
    okino
    0.07
     considerations
    0.06
    ä¸Ģä¸ĭ
    0.06
    wner
    0.06
    fone
    0.06
    Activations Density 0.051%

    No Known Activations