© 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. 106026
    Prev
    Next
    INDEX
    Explanations

    numerical data and web-related structures in content

    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
    :animated
    -0.06
     prag
    -0.05
    stadt
    -0.05
    anka
    -0.05
    ÑģÑĥ
    -0.05
     pace
    -0.05
     Kurt
    -0.05
    olini
    -0.05
    езд
    -0.05
     theirs
    -0.05
    POSITIVE LOGITS
    lesia
    0.08
     Ulus
    0.08
    ustil
    0.07
    Ĺi
    0.07
    efs
    0.07
     ulus
    0.07
    odon
    0.07
    Ñģклад
    0.07
    elpers
    0.07
     HttpMethod
    0.07
    Activations Density 0.001%

    No Known Activations