© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83405
    Prev
    Next
    INDEX
    Explanations

    terms related to return policies and conditions for returning items

    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
     =========================================================================
    -0.07
    볨
    -0.07
    uggage
    -0.07
     pym
    -0.07
    aho
    -0.06
    è¶Ĭ
    -0.06
    <context
    -0.06
    _managed
    -0.06
    blr
    -0.06
    ieties
    -0.06
    POSITIVE LOGITS
    783
    0.06
    611
    0.06
    ufs
    0.06
    uf
    0.06
    cre
    0.06
    оже
    0.06
     perish
    0.06
    ült
    0.06
    659
    0.06
    icare
    0.06
    Activations Density 0.003%

    No Known Activations