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. 56034
    Prev
    Next
    INDEX
    Explanations

    road and highway 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
     luck
    -0.07
    olulu
    -0.06
    ikt
    -0.06
    dera
    -0.06
     starving
    -0.06
     ><?
    -0.06
    cott
    -0.05
     inform
    -0.05
    æ¿
    -0.05
    dur
    -0.05
    POSITIVE LOGITS
    /Core
    0.07
    yen
    0.07
    (internal
    0.07
    /state
    0.07
     Lump
    0.07
    quina
    0.07
     Dawn
    0.07
    ainter
    0.06
    ?action
    0.06
    yte
    0.06
    Activations Density 0.005%

    No Known Activations