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. 21-LLAMASCOPE-RES-32K
    6. 16165
    Prev
    Next
    INDEX
    Explanations

    terms related to scheduling and availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieux
    -0.15
    atrix
    -0.15
    cel
    -0.15
     поÑģÑĤав
    -0.14
    chw
    -0.14
    aku
    -0.14
     onCancelled
    -0.14
    atal
    -0.14
    we
    -0.13
    Ø´ÙĨ
    -0.13
    POSITIVE LOGITS
     Bris
    0.16
    oris
    0.16
    indy
    0.16
    htub
    0.16
    åĩ¡
    0.16
    burgh
    0.16
    ]-$
    0.15
    esser
    0.15
    apus
    0.15
    harma
    0.15
    Activations Density 0.003%

    No Known Activations