© 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. 83145
    Prev
    Next
    INDEX
    Explanations

    programming language import statements and package declarations

    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
    rens
    -0.07
    atk
    -0.07
    vie
    -0.07
    .scalablytyped
    -0.06
    iÄį
    -0.06
    ilt
    -0.06
    ãģĸ
    -0.06
    odos
    -0.06
    isay
    -0.06
     ActionTypes
    -0.06
    POSITIVE LOGITS
    ltra
    0.08
    acular
    0.07
    .omg
    0.06
    ityEngine
    0.06
    racat
    0.06
    ancial
    0.06
    AccessType
    0.06
    experiment
    0.06
    .ObjectMeta
    0.06
    @student
    0.06
    Activations Density 0.010%

    No Known Activations