Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96184
    Prev
    Next
    INDEX
    Explanations

    references to cottages or similar types of small houses

    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
    nings
    -0.09
    eous
    -0.08
    ned
    -0.07
    Ỽt
    -0.07
    nem
    -0.07
    OrDefault
    -0.07
    ners
    -0.06
    nt
    -0.06
    utherford
    -0.06
    antes
    -0.06
    POSITIVE LOGITS
    etry
    0.07
    ázi
    0.07
    _ctl
    0.07
    ÑģÑĤÑĢи
    0.07
    ว
    0.06
    -type
    0.06
    ãģ¡ãģ¯
    0.06
    ÐłÐĺ
    0.06
    ackle
    0.06
    -style
    0.06
    Activations Density 0.003%

    No Known Activations