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. 6-LLAMASCOPE-RES-32K
    6. 7053
    Prev
    Next
    INDEX
    Explanations

    references to product identification and specifications

    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
    een
    -0.21
    ़
    -0.21
    gun
    -0.20
    gen
    -0.19
    gest
    -0.18
    gel
    -0.18
    gie
    -0.18
    g
    -0.18
    aus
    -0.18
    green
    -0.17
    POSITIVE LOGITS
    ucle
    0.28
    avigator
    0.23
    etwork
    0.22
    ned
    0.21
    ning
    0.21
    ecessary
    0.20
    avigate
    0.19
    atural
    0.19
    egative
    0.19
    labs
    0.19
    Activations Density 1.862%

    No Known Activations