© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 94442
    Prev
    Next
    INDEX
    Explanations

    characters or symbols, particularly non-standard or special characters

    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
    rana
    -0.09
    ��
    -0.08
    �
    -0.08
    ieval
    -0.08
    atura
    -0.07
    hta
    -0.07
    ���
    -0.07
    ����
    -0.07
    ÑģÑı
    -0.07
    NotNull
    -0.07
    POSITIVE LOGITS
     Uns
    0.07
    greens
    0.06
    onne
    0.06
    illac
    0.06
    pone
    0.06
    rier
    0.06
    TypeDef
    0.06
    gages
    0.06
    to
    0.06
     quadrant
    0.05
    Activations Density 0.003%

    No Known Activations