© 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. 77081
    Prev
    Next
    INDEX
    Explanations

    phrases related to value and affordability

    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
    80
    -0.06
    lio
    -0.06
     Pare
    -0.06
    itoris
    -0.06
    cke
    -0.06
    elia
    -0.05
    ince
    -0.05
     vic
    -0.05
    Ã
    -0.05
    -d
    -0.05
    POSITIVE LOGITS
    TickCount
    0.08
    leur
    0.07
    .scalablytyped
    0.07
    AGMA
    0.07
    .opensource
    0.07
     Synd
    0.07
    ãĤ·ãĤ¢
    0.07
    ovny
    0.07
    .opend
    0.07
    ipur
    0.07
    Activations Density 0.000%

    No Known Activations