© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 1603
    Prev
    Next
    INDEX
    Explanations

    concepts related to relief and escape from stress or discomfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    okt
    -0.16
     ucwords
    -0.15
    owards
    -0.14
     rezerv
    -0.14
    okit
    -0.14
    obec
    -0.13
    Reserved
    -0.13
    essim
    -0.13
     Reserved
    -0.13
    579
    -0.13
    POSITIVE LOGITS
     relief
    0.58
     res
    0.48
     Relief
    0.46
     rep
    0.44
     escape
    0.42
     relieve
    0.39
     refuge
    0.36
     release
    0.34
     resp
    0.33
     relie
    0.33
    Activations Density 0.252%

    No Known Activations