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. 7635
    Prev
    Next
    INDEX
    Explanations

    references to sports competitions and events

    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
    ampa
    -0.15
    ech
    -0.14
    yen
    -0.14
    arrant
    -0.14
    sut
    -0.13
    pla
    -0.13
    pees
    -0.13
     rentals
    -0.13
     inplace
    -0.13
    -thumbnail
    -0.13
    POSITIVE LOGITS
    osate
    0.14
    ritel
    0.14
    olor
    0.14
    orne
    0.13
    ymm
    0.13
    obox
    0.13
    like
    0.13
    Areas
    0.13
    }elseif
    0.13
    iban
    0.12
    Activations Density 0.005%

    No Known Activations