© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126514
    Prev
    Next
    INDEX
    Explanations

    references to neuroscience and related scientific fields

    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
    -ÑĤаки
    -0.08
    isman
    -0.07
    klä
    -0.07
    rescia
    -0.07
    arent
    -0.07
    akter
    -0.07
    riority
    -0.07
    antity
    -0.07
    иÑĤеÑĤ
    -0.07
    rosso
    -0.07
    POSITIVE LOGITS
    ụ
    0.07
     pall
    0.07
     Cumhur
    0.07
    pics
    0.06
    y
    0.06
    etti
    0.06
    ìłģ
    0.06
    ailable
    0.06
     Yard
    0.06
    ive
    0.06
    Activations Density 0.002%

    No Known Activations