© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56060
    Prev
    Next
    INDEX
    Explanations

    components related to research methodology and discussion

    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
    unting
    -0.07
    ores
    -0.07
    allo
    -0.07
    occo
    -0.07
    oller
    -0.06
    LIK
    -0.06
     Bere
    -0.06
    oram
    -0.06
    owers
    -0.06
    онд
    -0.06
    POSITIVE LOGITS
    emain
    0.06
     IEEE
    0.06
    *out
    0.06
     retros
    0.06
    tog
    0.06
     Recomm
    0.06
    odash
    0.06
    HideInInspector
    0.06
     út
    0.06
     covered
    0.06
    Activations Density 0.005%

    No Known Activations