© 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. 6-LLAMASCOPE-RES-32K
    6. 25460
    Prev
    Next
    INDEX
    Explanations

    references to time periods, specifically the frequency of the word "week."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orta
    -0.15
     Santa
    -0.15
    åĬŀ
    -0.14
    oji
    -0.14
    .DataAccess
    -0.14
     santa
    -0.14
    ãĥ³ãĥĹ
    -0.14
    -regexp
    -0.13
    idges
    -0.13
    ÃĸL
    -0.13
    POSITIVE LOGITS
     Bernstein
    0.16
    xAD
    0.14
     Cous
    0.14
    NTAX
    0.14
    icens
    0.13
     cabinet
    0.13
     Deliver
    0.13
     Dort
    0.13
    ABCDEFGHIJKLMNOP
    0.13
    ABA
    0.13
    Activations Density 0.021%

    No Known Activations