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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 125628
    Prev
    Next
    INDEX
    Explanations

    collocations involving the word "with."

    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
    ets
    -0.08
    yr
    -0.06
    دÙĩÙħ
    -0.06
    avian
    -0.06
     Julie
    -0.06
    ħ§
    -0.06
    azine
    -0.06
    pill
    -0.06
    .tencent
    -0.06
    اسÙĬ
    -0.06
    POSITIVE LOGITS
    pez
    0.07
    eeper
    0.07
    lesh
    0.07
    åijĬ
    0.06
    odore
    0.06
    aji
    0.06
     delay
    0.06
    isson
    0.06
    dl
    0.06
    olia
    0.06
    Activations Density 0.025%

    No Known Activations