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. 10-LLAMASCOPE-RES-32K
    6. 3867
    Prev
    Next
    INDEX
    Explanations

    descriptors related to tranquility and peaceful environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    via
    -0.15
    ham
    -0.14
    rote
    -0.14
    weep
    -0.14
    ouri
    -0.14
    ãĥ³ãĤ¬
    -0.14
    nite
    -0.14
    è£ľ
    -0.13
    HAM
    -0.13
    bart
    -0.13
    POSITIVE LOGITS
    anka
    0.19
    ãģ£ãģ±
    0.18
    .rc
    0.16
    onas
    0.16
    .ser
    0.15
    ünden
    0.15
    iesel
    0.15
    Äįka
    0.15
    OLEAN
    0.15
    ichert
    0.14
    Activations Density 0.065%

    No Known Activations