Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3679
    Prev
    Next
    INDEX
    Explanations

    terms related to marketing schemes and financial transactions

    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
    OTES
    -0.07
    åįļçī©
    -0.07
    SHOP
    -0.07
    ontrol
    -0.07
    lant
    -0.06
    OTP
    -0.06
    å²
    -0.06
    ngrx
    -0.06
    elan
    -0.06
    cak
    -0.06
    POSITIVE LOGITS
    /Dk
    0.07
    λλι
    0.06
     babe
    0.06
     territories
    0.06
    .builder
    0.06
     Join
    0.06
    strcasecmp
    0.06
     kit
    0.06
     Leader
    0.06
    (super
    0.06
    Activations Density 0.010%

    No Known Activations