© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 6549
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and their details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ến
    -0.15
    _depend
    -0.14
    jd
    -0.14
     Dep
    -0.14
     Singles
    -0.14
    DebugEnabled
    -0.13
     didSet
    -0.13
    ħn
    -0.13
     Relay
    -0.13
    anga
    -0.13
    POSITIVE LOGITS
    tÃŃ
    0.17
     Freeman
    0.14
    etimes
    0.14
     Bones
    0.14
    atoi
    0.14
    atore
    0.14
    itone
    0.13
    undy
    0.13
    INGER
    0.13
    Normalization
    0.13
    Activations Density 0.019%

    No Known Activations