© 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. 17-LLAMASCOPE-RES-131K
    6. 61160
    Prev
    Next
    INDEX
    Explanations

    phrases related to benefits and features of products or services

    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
    _outputs
    -0.06
    akis
    -0.06
    orld
    -0.06
     vi
    -0.06
    uos
    -0.05
    ków
    -0.05
    екÑģи
    -0.05
    WD
    -0.05
     rear
    -0.05
    terior
    -0.05
    POSITIVE LOGITS
     Custom
    0.07
     CORPOR
    0.07
     bulk
    0.07
     Bulk
    0.07
    ÑĤÑİ
    0.07
     denom
    0.07
    NullOrEmpty
    0.07
    Custom
    0.07
    Embed
    0.07
    akit
    0.07
    Activations Density 0.137%

    No Known Activations