Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 10771
    Prev
    Next
    INDEX
    Explanations

    variations and mentions of the word "clay."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alet
    -0.18
    ple
    -0.16
    scribe
    -0.15
    IVAL
    -0.15
    stad
    -0.15
    à¹īà¸ĩ
    -0.15
    icos
    -0.14
    eting
    -0.14
    yro
    -0.13
    GS
    -0.13
    POSITIVE LOGITS
    ton
    0.30
    tons
    0.25
     pigeon
    0.22
    TON
    0.22
    pool
    0.21
    tor
    0.21
    allee
    0.20
    ey
    0.20
    borne
    0.19
    bourne
    0.19
    Activations Density 0.008%

    No Known Activations