© 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. 17-LLAMASCOPE-RES-131K
    6. 57525
    Prev
    Next
    INDEX
    Explanations

    phrases related to rumors and community gossip

    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
    à¸¸à¸Ľ
    -0.06
     readability
    -0.06
    elves
    -0.06
    éĤ¦
    -0.06
    usto
    -0.06
     reads
    -0.06
     Walton
    -0.06
     pitch
    -0.06
    sÃŃ
    -0.06
     ance
    -0.06
    POSITIVE LOGITS
     gossip
    0.10
     rumor
    0.09
     rumors
    0.09
    åĿĬ
    0.08
     rum
    0.08
     rumours
    0.08
     grape
    0.08
    bare
    0.08
     spreading
    0.07
     whispers
    0.07
    Activations Density 0.046%

    No Known Activations