© 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. 30-LLAMASCOPE-RES-32K
    11. 3457
    Prev
    Next
    INDEX
    Explanations

    information related to medical conditions and their treatments, particularly focusing on concussions and other brain-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .googleapis
    -0.14
    cheme
    -0.14
    (OP
    -0.14
    earer
    -0.13
    ÑĢана
    -0.13
    ekim
    -0.13
     ydk
    -0.13
    ollower
    -0.13
     dynam
    -0.12
    tha
    -0.12
    POSITIVE LOGITS
     Unt
    0.26
    Sym
    0.25
    SYM
    0.24
     Seek
    0.23
    Unt
    0.22
    sym
    0.21
     Causes
    0.21
     Treatment
    0.21
     Symptoms
    0.21
     Left
    0.21
    Activations Density 0.116%

    No Known Activations