© 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. 78261
    Prev
    Next
    INDEX
    Explanations

    elements related to travel experiences and virtual exploration

    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
    adero
    -0.07
     dán
    -0.07
    ronym
    -0.07
     Portrait
    -0.07
    sei
    -0.07
    LAG
    -0.06
    arkan
    -0.06
    олÑİ
    -0.06
    altet
    -0.06
    ayscale
    -0.06
    POSITIVE LOGITS
     virtual
    0.20
    virtual
    0.17
     vic
    0.16
     Virtual
    0.16
    VIRTUAL
    0.14
    Virtual
    0.14
    _virtual
    0.12
    IRTUAL
    0.11
    	virtual
    0.11
    .virtual
    0.11
    Activations Density 0.102%

    No Known Activations