© 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. 57200
    Prev
    Next
    INDEX
    Explanations

    instances of the word "another" or its variations in different contexts

    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
     ï
    -0.07
     Teh
    -0.06
    åĢŁ
    -0.06
    401
    -0.06
    Âłk
    -0.06
    tls
    -0.06
    userinfo
    -0.05
     either
    -0.05
    ï
    -0.05
     sever
    -0.05
    POSITIVE LOGITS
     ebenfalls
    0.10
     equally
    0.10
     similarly
    0.10
     another
    0.09
    another
    0.09
     ìĹŃìĭľ
    0.08
    ylko
    0.08
    Another
    0.08
    anoia
    0.07
     Another
    0.07
    Activations Density 0.038%

    No Known Activations