© 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. 15-LLAMASCOPE-RES-131K
    6. 62160
    Prev
    Next
    INDEX
    Explanations

    elements related to trials or testing experiences

    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
    ESH
    -0.07
    elow
    -0.07
    emes
    -0.07
    esus
    -0.07
    kus
    -0.06
    .infinity
    -0.06
    geb
    -0.06
    ãģĴ
    -0.06
    egen
    -0.06
    inde
    -0.06
    POSITIVE LOGITS
    before
    0.07
    .getInteger
    0.06
    ãĥ³ãĥĦ
    0.06
    ampie
    0.06
     calend
    0.06
    akest
    0.06
     proof
    0.06
    atos
    0.06
    Restricted
    0.06
     Reform
    0.06
    Activations Density 0.010%

    No Known Activations