© 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. 82547
    Prev
    Next
    INDEX
    Explanations

    terms related to prophecy and prophetic literature

    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
    568
    -0.07
    isoft
    -0.06
    YNAM
    -0.06
    885
    -0.06
    ayout
    -0.06
    aise
    -0.06
    987
    -0.06
    ãģ°
    -0.06
    Descriptor
    -0.06
    567
    -0.06
    POSITIVE LOGITS
    ess
    0.09
    TEGER
    0.08
    QUIRE
    0.08
    esses
    0.07
    river
    0.07
    aniel
    0.07
    _DIRS
    0.07
    elm
    0.06
    ÑĢÑĸз
    0.06
    FromClass
    0.06
    Activations Density 0.007%

    No Known Activations