© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57054
    Prev
    Next
    INDEX
    Explanations

    numerical values related to financial performance and metrics

    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
    vern
    -0.08
    ipop
    -0.08
    опиÑģ
    -0.07
    ssf
    -0.07
    agate
    -0.07
    mere
    -0.07
    ldb
    -0.07
    nip
    -0.06
    ILED
    -0.06
    quer
    -0.06
    POSITIVE LOGITS
    oga
    0.08
    олÑİ
    0.06
    ]={↵
    0.06
    ersen
    0.06
    TestFixture
    0.06
    istrovstvÃŃ
    0.05
     neut
    0.05
    OLID
    0.05
     bis
    0.05
    636
    0.05
    Activations Density 0.005%

    No Known Activations