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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7232
    Prev
    Next
    INDEX
    Explanations

    references to historical and old structures or features

    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
     Paulo
    -0.15
    edd
    -0.14
    ioni
    -0.14
    åĿĬ
    -0.14
     unfavor
    -0.14
    KIT
    -0.14
     imped
    -0.13
     armies
    -0.13
     foot
    -0.13
    iamond
    -0.13
    POSITIVE LOGITS
    ahun
    0.17
    941
    0.17
    oreach
    0.16
    ruise
    0.15
    zek
    0.14
    AllWindows
    0.14
    ales
    0.14
    enet
    0.14
    OfDay
    0.14
    usan
    0.14
    Activations Density 0.067%

    No Known Activations