© 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. 87623
    Prev
    Next
    INDEX
    Explanations

    phrases concerning abandonment or things left behind

    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
    abh
    -0.07
    EGIN
    -0.07
    ilon
    -0.07
    rescia
    -0.07
    ypy
    -0.06
    why
    -0.06
    eum
    -0.06
    apy
    -0.06
    sto
    -0.06
    burg
    -0.06
    POSITIVE LOGITS
    wards
    0.08
    /left
    0.08
    odable
    0.07
    WARDED
    0.07
     Cole
    0.07
    /on
    0.07
    å¤ķ
    0.07
    /back
    0.07
    foot
    0.07
    à¥įà¤Ĺत
    0.07
    Activations Density 0.005%

    No Known Activations