© 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. 125936
    Prev
    Next
    INDEX
    Explanations

    mentions of specific sports teams or events

    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
    ÌĨ
    -0.08
    fsp
    -0.08
    ï¸
    -0.07
    aram
    -0.07
    ettel
    -0.07
    endir
    -0.07
    CHAN
    -0.07
    agrant
    -0.07
    奴
    -0.07
    elsey
    -0.07
    POSITIVE LOGITS
     team
    0.08
    team
    0.06
    eton
    0.06
    atat
    0.06
    æŀ
    0.06
     directive
    0.05
     Directive
    0.05
    ses
    0.05
    ª
    0.05
     delegation
    0.05
    Activations Density 0.013%

    No Known Activations