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. 3-LLAMASCOPE-RES-32K
    6. 24467
    Prev
    Next
    INDEX
    Explanations

    details about botanical characteristics and uses of plants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chances
    -0.16
    ÐŁÐļ
    -0.16
    polator
    -0.15
    anova
    -0.15
    mf
    -0.15
    /disable
    -0.14
     Regular
    -0.14
    .createFrom
    -0.14
    UNDLE
    -0.14
     bab
    -0.14
    POSITIVE LOGITS
     Dare
    0.15
    ayıp
    0.15
    ãĤ·ãĥ§
    0.14
     Simmons
    0.14
    ãĤ¤ãĥĦ
    0.14
    Nam
    0.14
    "."
    0.13
    mens
    0.13
     Lans
    0.13
    è¨
    0.13
    Activations Density 0.548%

    No Known Activations