© 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. 18-LLAMASCOPE-RES-32K
    11. 16106
    Prev
    Next
    INDEX
    Explanations

    references to names and entities related to geographical locations, especially in contexts involving art and community engagement

    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
    Å¡i
    -0.17
    les
    -0.14
    ophy
    -0.14
    ollar
    -0.14
    ping
    -0.14
    egg
    -0.14
    ~~~~~~~~
    -0.14
     tower
    -0.14
    pill
    -0.14
    еÑĢе
    -0.14
    POSITIVE LOGITS
    ousse
    0.17
    iqué
    0.16
    kker
    0.16
    ujet
    0.16
    WO
    0.15
    /archive
    0.15
    _mo
    0.15
    thood
    0.15
    atable
    0.15
    omo
    0.14
    Activations Density 0.102%

    No Known Activations