© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16598
    Prev
    Next
    INDEX
    Explanations

    phrases related to crossing boundaries and breaking barriers

    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
    indr
    -0.08
    haar
    -0.07
    ugi
    -0.07
    bia
    -0.06
    mlin
    -0.06
    ogl
    -0.06
    OTES
    -0.06
    rowable
    -0.06
    樹
    -0.06
    emm
    -0.06
    POSITIVE LOGITS
     boundaries
    0.25
     borders
    0.22
     boundary
    0.20
     border
    0.18
    boundary
    0.16
    Boundary
    0.15
     Borders
    0.15
    Borders
    0.15
    border
    0.14
     Boundary
    0.14
    Activations Density 0.069%

    No Known Activations