© 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. 40345
    Prev
    Next
    INDEX
    Explanations

    terms related to training material and assessments in a professional or technical context

    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
    aban
    -0.06
    epar
    -0.06
    -ÑĤо
    -0.06
     nice
    -0.06
     kinds
    -0.06
     really
    -0.06
    abouts
    -0.06
     kind
    -0.06
    -
    -0.06
     real
    -0.05
    POSITIVE LOGITS
    ROTO
    0.08
    anton
    0.08
     autogenerated
    0.07
    ÄĽÅĻ
    0.07
    usch
    0.07
    LOAT
    0.07
    Äįel
    0.07
    ãĤ¤ãĥ³ãĥĪ
    0.07
    .glide
    0.07
    allon
    0.07
    Activations Density 0.015%

    No Known Activations