© 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. 3-LLAMASCOPE-RES-32K
    6. 3617
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the inclusion or involvement of multiple elements or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oreach
    -0.15
    eres
    -0.15
    antan
    -0.14
    -Ta
    -0.14
     overshadow
    -0.13
    ashi
    -0.13
     thirsty
    -0.13
    _BROWSER
    -0.13
     thought
    -0.13
    izzer
    -0.13
    POSITIVE LOGITS
    ané
    0.16
    ÅĤy
    0.16
    oppins
    0.15
    estar
    0.15
    oscope
    0.15
    cket
    0.14
    ạ
    0.14
     Moran
    0.14
    alara
    0.13
    360
    0.13
    Activations Density 0.119%

    No Known Activations