© 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. 13-LLAMASCOPE-RES-32K
    6. 15594
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to sports and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achu
    -0.16
     Zeit
    -0.15
    asco
    -0.15
    atio
    -0.15
    imedia
    -0.14
    lon
    -0.14
    ASHBOARD
    -0.14
    ialis
    -0.14
    alian
    -0.14
    jom
    -0.14
    POSITIVE LOGITS
     Meaning
    0.17
    alink
    0.15
     meaning
    0.14
     buggy
    0.14
    .Bounds
    0.14
     пиÑī
    0.13
    arshal
    0.13
    __$
    0.13
    edd
    0.13
    éĿ
    0.13
    Activations Density 0.016%

    No Known Activations