© 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. 74734
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing cause-and-effect relationships

    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
    anca
    -0.08
    ahren
    -0.07
    .construct
    -0.06
    ReadStream
    -0.06
    olut
    -0.06
    ilestone
    -0.06
    жÑĥ
    -0.06
    ift
    -0.06
    utron
    -0.06
    _BLUE
    -0.06
    POSITIVE LOGITS
    å®ĥ
    0.11
     it
    0.10
     nó
    0.10
     à¤ĩसस
    0.09
     оно
    0.09
    inson
    0.08
    ï¼Įå®ĥ
    0.08
    å®ĥ们
    0.07
    è¿Ļæł·
    0.07
    ellas
    0.07
    Activations Density 0.077%

    No Known Activations