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. 126697
    Prev
    Next
    INDEX
    Explanations

    nouns related to business services and logistics

    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
    utom
    -0.07
    uf
    -0.07
     instead
    -0.07
    å½¼
    -0.06
     Berger
    -0.06
     Kop
    -0.06
     while
    -0.06
     rather
    -0.06
    ehr
    -0.06
    exus
    -0.06
    POSITIVE LOGITS
     alike
    0.09
     Äįi
    0.08
     whichever
    0.07
    eldom
    0.07
    glass
    0.07
    whatever
    0.07
    Whatever
    0.07
     Ù쨥ÙĨ
    0.07
     Äijá»ģu
    0.07
    137
    0.06
    Activations Density 0.024%

    No Known Activations