© 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. 55795
    Prev
    Next
    INDEX
    Explanations

    content related to teaching and learning methods

    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
    enia
    -0.08
    nic
    -0.08
     NIC
    -0.07
    NIC
    -0.07
    ÑĢÑĥ
    -0.07
    ideo
    -0.06
    agen
    -0.06
    ãĥĭãĥ¼
    -0.06
     educ
    -0.06
     wrest
    -0.06
    POSITIVE LOGITS
    ollo
    0.09
    alem
    0.08
    GetMethod
    0.08
    ptron
    0.07
    ÑĢеп
    0.07
     creo
    0.07
     kuru
    0.07
    ashion
    0.06
    _Style
    0.06
    άνÏī
    0.06
    Activations Density 0.007%

    No Known Activations