Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106558
    Prev
    Next
    INDEX
    Explanations

    geographic locations and their directional references

    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
    ajs
    -0.09
    atron
    -0.08
    OKIE
    -0.08
    obraz
    -0.08
    efon
    -0.08
     ÄĮer
    -0.07
    azel
    -0.07
    keit
    -0.07
    _DECLARE
    -0.07
    ensa
    -0.07
    POSITIVE LOGITS
    /right
    0.08
    /left
    0.07
     of
    0.06
    (lower
    0.06
    leaning
    0.06
     å£
    0.06
    üs
    0.06
     (
    0.05
     conv
    0.05
     counterpart
    0.05
    Activations Density 0.028%

    No Known Activations