© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 60253
    Prev
    Next
    INDEX
    Explanations

    elements related to hope, belief, and the relationship between systems and contexts in various scenarios

    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
    714
    -0.07
    zel
    -0.06
    isko
    -0.06
     waterfall
    -0.06
    ÐļÐĺ
    -0.06
    ngör
    -0.06
     Fuk
    -0.06
    dal
    -0.06
     Raum
    -0.06
    024
    -0.06
    POSITIVE LOGITS
    ube
    0.07
    uch
    0.06
    alie
    0.06
    @d
    0.06
    $insert
    0.06
     Madonna
    0.06
     baÅŁÄ±na
    0.06
     Hed
    0.06
    uchs
    0.06
     æ®
    0.06
    Activations Density 0.002%

    No Known Activations