© 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. 16767
    Prev
    Next
    INDEX
    Explanations

    actions and transitions related to relocation or movement

    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
    atas
    -0.08
     Representative
    -0.07
    ikel
    -0.07
    onal
    -0.07
     éĢģ
    -0.07
    ponge
    -0.07
    åĢĻ
    -0.07
    pike
    -0.07
    ách
    -0.07
    statt
    -0.07
    POSITIVE LOGITS
    istra
    0.05
    s
    0.05
     back
    0.05
     into
    0.05
    784
    0.05
     permanent
    0.05
    ydro
    0.05
    ØŃÙĤ
    0.05
     toItem
    0.05
    OCUS
    0.05
    Activations Density 0.009%

    No Known Activations