© 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. 78081
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity or character associated with the name "Arm."

    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
    oming
    -0.07
    миниÑģÑĤÑĢа
    -0.07
    ader
    -0.07
     suprem
    -0.07
    ames
    -0.07
    loat
    -0.06
    ibre
    -0.06
    jur
    -0.06
    opr
    -0.06
     Integral
    -0.06
    POSITIVE LOGITS
    XE
    0.08
    rest
    0.07
    ature
    0.07
    ful
    0.07
    okud
    0.07
     buried
    0.07
    fully
    0.07
    atures
    0.07
    illary
    0.06
     Harm
    0.06
    Activations Density 0.008%

    No Known Activations