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. 11255
    Prev
    Next
    INDEX
    Explanations

    prominent brands and specific products related to fashion and entertainment

    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
    éis
    -0.18
    .synthetic
    -0.16
    usc
    -0.16
    uar
    -0.16
    ãģĬãĤĬ
    -0.16
    loan
    -0.16
    lož
    -0.16
    ouver
    -0.15
     spare
    -0.15
    essed
    -0.15
    POSITIVE LOGITS
    -स
    0.18
    vation
    0.17
    urai
    0.17
    chez
    0.17
    tember
    0.17
    izophren
    0.17
    bastian
    0.17
    posium
    0.16
    -sided
    0.16
    isbury
    0.16
    Activations Density 1.911%

    No Known Activations