Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 26038
    Prev
    Next
    INDEX
    Explanations

    casual conversational phrases and transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alright
    -0.15
    æ¬
    -0.14
    ĥn
    -0.13
    uala
    -0.13
     einfach
    -0.13
    tright
    -0.13
    __).
    -0.13
     eget
    -0.13
    ç½
    -0.13
    imson
    -0.13
    POSITIVE LOGITS
     note
    0.19
     speaking
    0.19
     unrelated
    0.18
     don
    0.18
     yes
    0.17
    Speaking
    0.17
     Speaking
    0.17
    rex
    0.16
     did
    0.15
     btw
    0.15
    Activations Density 0.135%

    No Known Activations