© 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. 125861
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating spatial relationships

    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
    _$_
    -0.07
    Įĵ
    -0.07
     ÐĴики
    -0.07
    ternet
    -0.07
    anik
    -0.06
    ocale
    -0.06
     пÑĸдÑģ
    -0.06
    .Undef
    -0.06
    .Temp
    -0.06
     तह
    -0.06
    POSITIVE LOGITS
     nearest
    0.10
     center
    0.08
     centre
    0.07
    nearest
    0.07
     edge
    0.07
    ought
    0.06
    oll
    0.06
     point
    0.06
    center
    0.06
    touch
    0.06
    Activations Density 0.039%

    No Known Activations