© 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. 15-LLAMASCOPE-RES-131K
    11. 90435
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific measurements or experimental data

    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
    arken
    -0.08
    å¡ļ
    -0.07
    hammad
    -0.07
    Versions
    -0.07
     же
    -0.07
    esian
    -0.07
    ilog
    -0.07
    leases
    -0.07
    arty
    -0.07
    ilver
    -0.07
    POSITIVE LOGITS
    ron
    0.06
    ICA
    0.06
    th
    0.06
    ter
    0.06
    858
    0.06
    ownt
    0.06
    enary
    0.06
    ove
    0.05
    otas
    0.05
    iв
    0.05
    Activations Density 0.011%

    No Known Activations