© 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. 125958
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms related to APIs and permissions, particularly for Facebook and similar applications

    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
    imbus
    -0.08
    ãĥĥãĥĹ
    -0.08
    алÑĥ
    -0.08
    hone
    -0.08
    anki
    -0.08
     jedn
    -0.08
    _FD
    -0.07
    affer
    -0.07
    ãģıãģł
    -0.07
    alytics
    -0.07
    POSITIVE LOGITS
    ↵
    0.06
    mong
    0.06
    /of
    0.05
    icus
    0.05
     –
    0.05
    ic
    0.05
     totally
    0.05
     ...
    0.05
    801
    0.05
    802
    0.05
    Activations Density 0.009%

    No Known Activations