© 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. 125533
    Prev
    Next
    INDEX
    Explanations

    parameters related to choices or decisions influenced by various factors

    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
    orsch
    -0.07
    kul
    -0.07
    á»ħ
    -0.07
     Potion
    -0.07
    _CS
    -0.06
    ì±Ħ
    -0.06
    reamble
    -0.06
    ARRANT
    -0.06
    iona
    -0.06
    plete
    -0.06
    POSITIVE LOGITS
     desired
    0.10
     budget
    0.10
     wants
    0.09
     desires
    0.08
     preference
    0.08
     goals
    0.08
     wanted
    0.08
     Desired
    0.08
     preferences
    0.08
    budget
    0.08
    Activations Density 0.016%

    No Known Activations