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. 14-LLAMASCOPE-RES-32K
    6. 31933
    Prev
    Next
    INDEX
    Explanations

    specific phrases indicating actions and cognitive states involving understanding, planning, and future outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lus
    -0.16
     Jet
    -0.16
    .ColumnHeader
    -0.15
       
    -0.15
    oton
    -0.14
    égor
    -0.14
    ÑĨев
    -0.14
    ensen
    -0.14
     wal
    -0.14
    hand
    -0.14
    POSITIVE LOGITS
     happening
    0.22
     happens
    0.21
     happened
    0.20
     happen
    0.20
    ToDo
    0.18
    done
    0.17
     aconte
    0.16
    _done
    0.16
     Happ
    0.16
    åıijçĶŁ
    0.16
    Activations Density 0.204%

    No Known Activations