© 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. 5960
    Prev
    Next
    INDEX
    Explanations

    references to the weekend and specific days related to events or actions that occurred during that time

    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
    ɵ
    -0.16
    orer
    -0.15
    orrent
    -0.15
    .scalablytyped
    -0.15
    avirus
    -0.15
    xico
    -0.15
    γε
    -0.14
    кÑĤа
    -0.14
    /Internal
    -0.14
    ookies
    -0.14
    POSITIVE LOGITS
    ilo
    0.17
    ing
    0.15
    161
    0.15
    stu
    0.15
    lege
    0.15
    ãĥ¼ãĥ
    0.14
    ION
    0.14
    160
    0.14
    981
    0.14
    fer
    0.14
    Activations Density 0.033%

    No Known Activations