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. 15-LLAMASCOPE-RES-32K
    6. 25387
    Prev
    Next
    INDEX
    Explanations

    references to biochemical mechanisms and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abaj
    -0.16
    iders
    -0.15
    akis
    -0.15
    xea
    -0.14
    esco
    -0.14
    agi
    -0.14
     gren
    -0.14
    postalcode
    -0.14
    bsolute
    -0.13
    instanc
    -0.13
    POSITIVE LOGITS
     mechanisms
    0.33
     mechanism
    0.33
     Mechan
    0.24
     mechan
    0.20
     explanation
    0.19
     maybe
    0.18
     perhaps
    0.17
     somewhere
    0.17
    Mech
    0.17
     Explanation
    0.16
    Activations Density 0.097%

    No Known Activations