© 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. 18-LLAMASCOPE-RES-32K
    6. 1617
    Prev
    Next
    INDEX
    Explanations

    mentions of the name Christopher, indicating significant references to individuals with that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Paths
    -0.15
    rico
    -0.15
    ãĥķãĥĪ
    -0.14
     ----------------------------------------------------------------------------↵
    -0.14
    ضÙħ
    -0.14
    ãģ£ãģį
    -0.14
    unate
    -0.14
    ERT
    -0.14
    ãĥªãĥ³ãĤ°
    -0.14
    undance
    -0.14
    POSITIVE LOGITS
    ä»¶
    0.15
     Columbus
    0.14
    allee
    0.14
    ÄĽÅ¾
    0.14
    privacy
    0.14
    ze
    0.14
     fa
    0.14
    truth
    0.14
    zik
    0.14
    ildren
    0.14
    Activations Density 0.014%

    No Known Activations