© 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. 15-LLAMASCOPE-RES-131K
    11. 103798
    Prev
    Next
    INDEX
    Explanations

    various forms of the prefix "ri" and the substring "atri"

    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
    ed
    -0.09
    ene
    -0.08
    rons
    -0.08
    acre
    -0.07
    ะ
    -0.07
    eld
    -0.07
    endar
    -0.07
    endo
    -0.07
    ens
    -0.07
    ged
    -0.07
    POSITIVE LOGITS
    er
    0.14
    erer
    0.10
    eri
    0.09
    ighth
    0.09
    hyth
    0.09
    iginal
    0.08
    polator
    0.08
    eria
    0.08
    erus
    0.08
    eam
    0.08
    Activations Density 0.055%

    No Known Activations