Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95998
    Prev
    Next
    INDEX
    Explanations

    references to subscriptions and newsletters

    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
    ars
    -0.07
    isson
    -0.06
    agine
    -0.05
    arsi
    -0.05
    ego
    -0.05
     et
    -0.05
    egal
    -0.05
     bow
    -0.05
    ux
    -0.05
     that
    -0.05
    POSITIVE LOGITS
    大åħ¨
    0.08
    à¥ģà¤ļ
    0.08
    374
    0.08
     tes
    0.07
    654
    0.07
    SSIP
    0.07
    iqueta
    0.07
    405
    0.07
    ï¼Ń
    0.07
    tran
    0.07
    Activations Density 0.005%

    No Known Activations