© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 57766
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that imply a conclusion or important information

    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
    łģ
    -0.07
     Dit
    -0.07
    icket
    -0.07
     bells
    -0.06
    lando
    -0.06
    ogram
    -0.06
    ither
    -0.06
     ------>
    -0.06
    trip
    -0.06
    rijk
    -0.06
    POSITIVE LOGITS
    Fi
    0.06
    /=
    0.06
    DataStream
    0.06
    isyon
    0.06
     ÐĿаÑģ
    0.06
    iculos
    0.06
    _resize
    0.06
    ettle
    0.06
    åľ
    0.06
    \Eloquent
    0.06
    Activations Density 0.004%

    No Known Activations