© 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. 5-LLAMASCOPE-RES-131K
    11. 125992
    Prev
    Next
    INDEX
    Explanations

    phrases related to journeys or quests

    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
    uder
    -0.09
    icari
    -0.08
    icina
    -0.07
    ÑģоÑĤ
    -0.07
    ovan
    -0.07
    bler
    -0.07
    ovenant
    -0.07
    iov
    -0.07
    ForRow
    -0.07
    idth
    -0.07
    POSITIVE LOGITS
    ly
    0.09
    ion
    0.07
    cc
    0.06
    es
    0.06
    ghi
    0.06
    lamaz
    0.06
    ial
    0.06
    a
    0.06
    ivals
    0.06
     Milo
    0.06
    Activations Density 0.003%

    No Known Activations