© 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. 74842
    Prev
    Next
    INDEX
    Explanations

    numerical data related to sampling rates or quantities

    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
    obil
    -0.07
    _BINARY
    -0.07
    undle
    -0.07
    ritch
    -0.07
    UNDLE
    -0.07
    inputEmail
    -0.07
    itung
    -0.07
    Äįka
    -0.07
    ulis
    -0.07
    cala
    -0.07
    POSITIVE LOGITS
     Freed
    0.06
    336
    0.06
     Smoke
    0.06
    detach
    0.06
    arge
    0.06
     Ash
    0.06
     appropri
    0.06
     bounce
    0.05
    axed
    0.05
    iez
    0.05
    Activations Density 0.000%

    No Known Activations