© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 76648
    Prev
    Next
    INDEX
    Explanations

    elements related to geographical descriptions and comparisons

    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
     oceans
    -0.07
    699
    -0.06
     ocean
    -0.06
    rir
    -0.06
     implicit
    -0.06
    inet
    -0.06
    acket
    -0.06
    waters
    -0.06
     ferry
    -0.06
     foreign
    -0.06
    POSITIVE LOGITS
     terrestrial
    0.12
     land
    0.11
     dry
    0.11
     inland
    0.10
     Dry
    0.09
    éĻ¸
    0.09
    dry
    0.09
    .land
    0.09
     dryer
    0.08
    land
    0.08
    Activations Density 0.063%

    No Known Activations