© 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. 126455
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to annotations in programming, particularly in the context of using libraries like Gson

    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
    .AF
    -0.07
    ampo
    -0.07
     ÙĨØŃ
    -0.06
    ERSHEY
    -0.06
    _transient
    -0.06
    253
    -0.06
    .ready
    -0.06
    886
    -0.06
    Äįe
    -0.06
    @Id
    -0.06
    POSITIVE LOGITS
     applied
    0.12
    Applied
    0.08
     Applied
    0.08
     ë¶Ļ
    0.07
     Bbw
    0.06
    жив
    0.06
    adt
    0.06
    CW
    0.06
     attached
    0.06
    ä»ĺãģį
    0.06
    Activations Density 0.028%

    No Known Activations