Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96023
    Prev
    Next
    INDEX
    Explanations

    instances of the word "accessed" or its variations

    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
    Calibri
    -0.06
    /Runtime
    -0.06
    olas
    -0.06
    ity
    -0.06
    .ua
    -0.06
    ityEngine
    -0.06
    folk
    -0.06
    zych
    -0.06
    ÐļТ
    -0.06
    adel
    -0.05
    POSITIVE LOGITS
    gle
    0.08
    isoft
    0.07
    okit
    0.07
     MyBase
    0.07
    iare
    0.07
    horia
    0.07
    JECT
    0.06
    okers
    0.06
    177
    0.06
    ãģĦãģ§
    0.06
    Activations Density 0.001%

    No Known Activations