© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118567
    Prev
    Next
    INDEX
    Explanations

    indicators of public opinion and support for political independence

    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
    aura
    -0.08
     WaitForSeconds
    -0.07
     damer
    -0.07
    senal
    -0.07
    acimiento
    -0.07
    impan
    -0.07
    freeze
    -0.07
     FindObjectOfType
    -0.07
    olia
    -0.07
    keleton
    -0.07
    POSITIVE LOGITS
     internals
    0.06
    æĦıè§ģ
    0.06
     Flip
    0.06
     approval
    0.05
     opinion
    0.05
    izont
    0.05
    ARGIN
    0.05
    AAD
    0.05
    752
    0.05
    543
    0.05
    Activations Density 0.005%

    No Known Activations