© 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. 5-LLAMASCOPE-RES-131K
    11. 125924
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly related to financial transactions and statistics

    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
     mak
    -0.07
    ataka
    -0.06
     rep
    -0.06
    inka
    -0.06
    ecs
    -0.06
    å±±å¸Ĥ
    -0.06
    ene
    -0.06
    è
    -0.06
    ocale
    -0.06
     hers
    -0.06
    POSITIVE LOGITS
    das
    0.07
    adas
    0.07
    :Add
    0.06
    коÑĢиÑģÑĤ
    0.06
    .converter
    0.06
    unde
    0.06
    postal
    0.06
    oud
    0.06
    .XR
    0.06
    adia
    0.06
    Activations Density 0.005%

    No Known Activations