© 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. 5-LLAMASCOPE-RES-131K
    6. 126573
    Prev
    Next
    INDEX
    Explanations

    references to specific items or characteristics

    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
    opsy
    -0.06
     Ange
    -0.06
    ober
    -0.06
     cell
    -0.06
    aura
    -0.06
     Cob
    -0.06
     erst
    -0.05
    anken
    -0.05
    tober
    -0.05
     habit
    -0.05
    POSITIVE LOGITS
     declaración
    0.07
    _mex
    0.07
     nackte
    0.07
    _ATOMIC
    0.07
    orial
    0.07
    ÙĪØŃ
    0.07
    èª
    0.07
    .Guna
    0.07
    .simps
    0.07
    ogh
    0.07
    Activations Density 0.000%

    No Known Activations