© 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. 24-LLAMASCOPE-RES-32K
    6. 5611
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the initiation or progression of actions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     continue
    -0.22
    continue
    -0.21
     continued
    -0.20
     continuing
    -0.20
     continuation
    -0.18
     continues
    -0.18
     continu
    -0.17
    continued
    -0.17
    	continue
    -0.17
     continuar
    -0.17
    POSITIVE LOGITS
    ying
    0.18
     поба
    0.17
     NOTICE
    0.17
     notice
    0.17
    Feel
    0.16
    TLS
    0.15
     taper
    0.15
    lesh
    0.15
     noticing
    0.15
     noticed
    0.15
    Activations Density 0.058%

    No Known Activations