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. 25-LLAMASCOPE-RES-32K
    6. 17987
    Prev
    Next
    INDEX
    Explanations

    phrases related to solutions and problem-solving processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĩºäºĨ
    -0.20
    äºĨä¸Ģ
    -0.18
    ä¸ĬäºĨ
    -0.17
    inded
    -0.17
    æĪIJäºĨ
    -0.16
    åΰäºĨ
    -0.16
    tered
    -0.15
    ivated
    -0.15
    ulates
    -0.15
    ted
    -0.15
    POSITIVE LOGITS
    иÑĤÑĮ
    0.33
    owaÄĩ
    0.30
    zyÄĩ
    0.29
    нÑĥÑĤÑĮ
    0.28
    аÑĤÑĮ
    0.28
    оваÑĤÑĮ
    0.27
    aÄĩ
    0.24
    ваÑĤÑĮ
    0.23
    ниÑĤÑĮ
    0.23
    izzare
    0.22
    Activations Density 0.052%

    No Known Activations