© 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. 105970
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to elevation and support structures

    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
    quals
    -0.07
    ocator
    -0.07
    éŃ
    -0.06
    icl
    -0.06
    ehr
    -0.06
    OOM
    -0.06
     Ñĥк
    -0.06
    èĤĥ
    -0.06
    posables
    -0.06
     Rug
    -0.06
    POSITIVE LOGITS
     suspension
    0.08
     suspended
    0.07
     ground
    0.07
     Suspension
    0.07
     raised
    0.07
     susp
    0.07
     Tick
    0.07
    AdapterFactory
    0.06
    MethodInfo
    0.06
     supra
    0.06
    Activations Density 0.020%

    No Known Activations