Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 29-LLAMASCOPE-RES-32K
    6. 12467
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to inversion or negative changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dac
    -0.14
    -upper
    -0.14
    atri
    -0.14
    lescope
    -0.14
    iran
    -0.14
    ampo
    -0.13
    IODevice
    -0.13
    .upper
    -0.13
    dbo
    -0.13
    ursor
    -0.13
    POSITIVE LOGITS
     down
    1.71
     Down
    1.52
    down
    1.45
    Down
    1.44
    -down
    1.43
     DOWN
    1.38
    _down
    1.23
    DOWN
    1.21
    .down
    1.19
    _DOWN
    1.02
    Activations Density 1.147%

    No Known Activations