© 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. 40253
    Prev
    Next
    INDEX
    Explanations

    phrases related to summoning or calling forth something

    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
    elog
    -0.07
    pointer
    -0.06
    reira
    -0.06
    eward
    -0.06
    mitters
    -0.06
    alon
    -0.06
    Ùģاع
    -0.06
    ymb
    -0.06
    enburg
    -0.06
    emetery
    -0.06
    POSITIVE LOGITS
     forth
    0.11
    ously
    0.08
     dib
    0.07
    onto
    0.07
     summoned
    0.07
    obil
    0.07
    ption
    0.07
     summon
    0.07
    UserCode
    0.07
    gary
    0.07
    Activations Density 0.006%

    No Known Activations