© 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. 5-LLAMASCOPE-RES-131K
    6. 125910
    Prev
    Next
    INDEX
    Explanations

    terms related to planning, optimization, and problem-solving strategies

    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
    ãĤ¾
    -0.07
    ucc
    -0.07
    _trait
    -0.07
     lep
    -0.06
     æº
    -0.06
    éŃļ
    -0.06
    éĺħ读次æķ°
    -0.06
    loit
    -0.06
    Plot
    -0.06
    chet
    -0.06
    POSITIVE LOGITS
    ilig
    0.07
     Koh
    0.06
    å±Ģ
    0.06
    orr
    0.06
    عار
    0.06
    ensen
    0.06
    dik
    0.06
    adin
    0.06
    oria
    0.06
    ackbar
    0.06
    Activations Density 0.004%

    No Known Activations