© 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. 31-LLAMASCOPE-RES-32K
    11. 1923
    Prev
    Next
    INDEX
    Explanations

    references to self-identity and personal development concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CastException
    -0.12
     Fucked
    -0.12
    .openConnection
    -0.11
    ¦æĥħ
    -0.11
    YPD
    -0.11
    eyin
    -0.11
    .mvp
    -0.11
    ookies
    -0.11
    θή
    -0.11
    ulos
    -0.11
    POSITIVE LOGITS
     self
    1.66
     Self
    1.46
    self
    1.38
    -self
    1.34
     SELF
    1.29
    Self
    1.25
    (self
    1.17
    /self
    1.16
    	self
    1.11
    =self
    1.10
    Activations Density 0.273%

    No Known Activations