© 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. 57700
    Prev
    Next
    INDEX
    Explanations

    sentences that include the phrase "this is" or similar variations indicating a statement or description

    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
    igo
    -0.06
    ordan
    -0.06
    Äĩ
    -0.06
     gó
    -0.05
    enty
    -0.05
    agn
    -0.05
    i
    -0.05
    amed
    -0.05
    ÅŁt
    -0.05
    top
    -0.05
    POSITIVE LOGITS
    istrovstvÃŃ
    0.08
    ssid
    0.07
    gnu
    0.07
    Uvs
    0.07
    arshal
    0.07
    ertz
    0.07
    uess
    0.07
    rant
    0.07
    427
    0.07
    zing
    0.07
    Activations Density 0.020%

    No Known Activations