© 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. 3247
    Prev
    Next
    INDEX
    Explanations

    important numerical statistics and values in the text

    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
    erç
    -0.07
    egr
    -0.07
    olumn
    -0.06
    olec
    -0.06
    ÄĻż
    -0.06
    íĴ
    -0.06
     Steel
    -0.06
    046
    -0.06
    rous
    -0.06
    assic
    -0.06
    POSITIVE LOGITS
    åıĬåħ¶
    0.08
    ORE
    0.07
    vala
    0.07
     threesome
    0.06
    iese
    0.06
    aci
    0.06
     ÙĨÙĤØ´Ùĩ
    0.06
    Associated
    0.06
    including
    0.06
    yon
    0.06
    Activations Density 0.052%

    No Known Activations