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. 23-LLAMASCOPE-RES-32K
    6. 27971
    Prev
    Next
    INDEX
    Explanations

    terms related to influence and the implications of financial or legal pressure on various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollower
    -0.15
    emode
    -0.14
    ertos
    -0.14
    918
    -0.14
    736
    -0.14
    _blob
    -0.13
    terra
    -0.13
     miracle
    -0.13
    cbd
    -0.13
    åĥ
    -0.13
    POSITIVE LOGITS
     greater
    0.29
     considerable
    0.28
    greater
    0.27
     maximal
    0.24
     minimal
    0.23
     greatest
    0.23
     immense
    0.23
     extensive
    0.23
     strong
    0.23
    minimal
    0.22
    Activations Density 0.222%

    No Known Activations