© 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. 15-LLAMASCOPE-RES-32K
    11. 1750
    Prev
    Next
    INDEX
    Explanations

    phrases and actions related to individual agency and empowering choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĥ½
    -0.24
    èĥ½å¤Ł
    -0.20
     kunnen
    -0.16
    çĦ¶
    -0.16
    orge
    -0.16
    æľį
    -0.15
    amaz
    -0.15
     pouvoir
    -0.15
    eree
    -0.15
     frequ
    -0.14
    POSITIVE LOGITS
     easily
    0.23
     feas
    0.21
     anytime
    0.20
     safely
    0.17
    inx
    0.17
     Easily
    0.17
    à¹Įà¹Ħà¸Ķ
    0.16
     snadno
    0.16
     be
    0.16
    ัà¸Ļà¹Ħà¸Ķ
    0.16
    Activations Density 1.093%

    No Known Activations