© 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. 76690
    Prev
    Next
    INDEX
    Explanations

    numbered or bullet-pointed items and lists

    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
    aler
    -0.07
    awe
    -0.07
    TRA
    -0.07
    etri
    -0.07
    adla
    -0.07
    订
    -0.07
    ifo
    -0.07
    á»ĭ
    -0.06
    enga
    -0.06
    ognito
    -0.06
    POSITIVE LOGITS
    รà¸ģ
    0.06
    æĪ¿
    0.06
    олÑİ
    0.06
    stantiate
    0.06
    :Object
    0.06
    æĹıèĩªæ²»
    0.06
     Thread
    0.06
     Gilbert
    0.06
    icable
    0.06
     Ridley
    0.06
    Activations Density 0.001%

    No Known Activations