© 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. 15-LLAMASCOPE-RES-131K
    6. 26958
    Prev
    Next
    INDEX
    Explanations

    variations of the suffix "er" related to names or roles

    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
    outil
    -0.08
     Amerik
    -0.08
    ãģĿãģĹãģ¦
    -0.07
    vak
    -0.07
    unde
    -0.07
    ande
    -0.07
    .protobuf
    -0.07
    ơi
    -0.07
     Franken
    -0.07
    andex
    -0.07
    POSITIVE LOGITS
    onz
    0.06
    aylight
    0.06
    197
    0.05
    194
    0.05
    rick
    0.05
     Editorial
    0.05
    193
    0.05
     BITTE
    0.05
    TRGL
    0.05
    hari
    0.05
    Activations Density 0.004%

    No Known Activations