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. 11-LLAMASCOPE-RES-32K
    6. 18162
    Prev
    Next
    INDEX
    Explanations

    specific geographical references or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nya
    -0.32
    ness
    -0.27
    ne
    -0.26
    ma
    -0.26
    rou
    -0.24
    ro
    -0.24
    me
    -0.24
    no
    -0.24
    ri
    -0.24
    nee
    -0.24
    POSITIVE LOGITS
    'nun
    0.21
    ’nun
    0.20
    gether
    0.19
    ffset
    0.19
    alesce
    0.18
    aes
    0.17
    ject
    0.17
    suit
    0.17
    ître
    0.17
    bservable
    0.17
    Activations Density 1.015%

    No Known Activations