© 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. 29641
    Prev
    Next
    INDEX
    Explanations

    references to geographical directions or regions, particularly focusing on "East" and "Eastern."

    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
    ubb
    -0.07
    ument
    -0.07
    kla
    -0.07
    arlo
    -0.07
    StateMachine
    -0.07
    iveau
    -0.07
    aison
    -0.07
    ëĿ½
    -0.07
    eliac
    -0.06
    éric
    -0.06
    POSITIVE LOGITS
    ablish
    0.12
    ward
    0.09
    ern
    0.09
    ERN
    0.08
    ensibly
    0.08
    gard
    0.07
    ensor
    0.07
    wing
    0.07
    à¹Ģà¸ī
    0.07
    erner
    0.07
    Activations Density 0.034%

    No Known Activations