© 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. 25-LLAMASCOPE-RES-32K
    11. 17027
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional experience and job roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atica
    -0.15
    /topics
    -0.15
     Äijón
    -0.13
    skb
    -0.13
    STEM
    -0.13
    osc
    -0.13
    ãĤ¤ãĥ³ãĥĪ
    -0.13
     Stamina
    -0.13
    æº
    -0.13
     èIJ
    -0.12
    POSITIVE LOGITS
     spells
    0.49
     spell
    0.46
     st
    0.43
     Spells
    0.38
     stint
    0.38
     brief
    0.35
    spell
    0.35
     SPELL
    0.35
     periods
    0.34
     Spell
    0.33
    Activations Density 0.146%

    No Known Activations