© 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. 78112
    Prev
    Next
    INDEX
    Explanations

    instances of interviews and appointments in a formal context

    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
    ÙĪاÙĩ
    -0.07
     kå
    -0.07
    ,:,:
    -0.07
    OKEN
    -0.07
    annonce
    -0.07
    OGLE
    -0.06
     Leban
    -0.06
     helicopt
    -0.06
    вид
    -0.06
    RefPtr
    -0.06
    POSITIVE LOGITS
    PFN
    0.06
    ornado
    0.06
     (*(
    0.06
    eless
    0.06
    implify
    0.05
    HF
    0.05
     respective
    0.05
     reference
    0.05
     Pocket
    0.05
    NH
    0.05
    Activations Density 0.004%

    No Known Activations