© 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. 15-LLAMASCOPE-RES-131K
    6. 90246
    Prev
    Next
    INDEX
    Explanations

    references to various types of organizations and roles within different contexts

    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
    /or
    -0.08
    aro
    -0.06
     rig
    -0.06
    NDER
    -0.06
     Holl
    -0.06
     Cock
    -0.06
     Noon
    -0.05
     Stack
    -0.05
    strap
    -0.05
    amon
    -0.05
    POSITIVE LOGITS
    acles
    0.08
    ients
    0.08
    phans
    0.07
    anges
    0.07
    esus
    0.07
    athed
    0.07
    ennen
    0.07
    grav
    0.07
    itat
    0.07
    anean
    0.07
    Activations Density 0.079%

    No Known Activations