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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95798
    Prev
    Next
    INDEX
    Explanations

    trends and standards related to IT service management

    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
    ami
    -0.06
     enemy
    -0.05
     Kane
    -0.05
    åł
    -0.05
     conting
    -0.05
    undler
    -0.05
    arn
    -0.05
    omid
    -0.05
    ulong
    -0.05
     Hanna
    -0.05
    POSITIVE LOGITS
     yacc
    0.08
    rosis
    0.08
    skirts
    0.07
    lant
    0.07
    lz
    0.07
    oples
    0.07
    yen
    0.07
    اÙĦÙģ
    0.07
    pdf
    0.07
    rium
    0.07
    Activations Density 0.011%

    No Known Activations