© 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. 106813
    Prev
    Next
    INDEX
    Explanations

    phrases indicating times and contexts of events

    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
    ÑģÑĮого
    -0.09
    θι
    -0.08
    ÑĶÑĹ
    -0.08
    ãĤ§
    -0.08
    esub
    -0.08
    ?url
    -0.07
    ,www
    -0.07
     EÅŁ
    -0.07
    #ac
    -0.07
    Âłtom
    -0.07
    POSITIVE LOGITS
     whereas
    0.07
    -fontawesome
    0.06
    herits
    0.06
    bie
    0.06
    ym
    0.06
    lys
    0.06
     while
    0.05
    ãģ¾ãĤĬ
    0.05
     AND
    0.05
    iÄĩ
    0.05
    Activations Density 0.082%

    No Known Activations