© 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. 76235
    Prev
    Next
    INDEX
    Explanations

    structured data and elements indicative of programming or software components

    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
    ctors
    -0.07
    lettes
    -0.07
     Oregon
    -0.06
    pies
    -0.06
    zier
    -0.06
    pie
    -0.06
    ê¶ģ
    -0.06
    Oregon
    -0.06
    -Methods
    -0.06
    .ini
    -0.06
    POSITIVE LOGITS
     Dro
    0.08
    kubectl
    0.08
     Ranch
    0.07
     Kubernetes
    0.07
     Pods
    0.07
    attle
    0.07
    _Construct
    0.07
    plx
    0.07
     Afghan
    0.07
     Helm
    0.07
    Activations Density 0.035%

    No Known Activations