© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6294
    Prev
    Next
    INDEX
    Explanations

    instances of the word "share" and related concepts, indicating a focus on sharing experiences and knowledge

    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
    echan
    -0.15
    ело
    -0.14
    ape
    -0.14
    331
    -0.14
    las
    -0.13
     éĻ
    -0.13
    _VISIBLE
    -0.12
    .Directory
    -0.12
     compliments
    -0.12
    shield
    -0.12
    POSITIVE LOGITS
    ABCDEFGHI
    0.17
    689
    0.15
    vier
    0.15
    699
    0.15
    049
    0.15
    kiye
    0.14
    å¿
    0.14
    ãĤ¿ãĥ³
    0.14
    enes
    0.14
    æĨ
    0.14
    Activations Density 0.048%

    No Known Activations