Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 18-LLAMASCOPE-RES-32K
    6. 16497
    Prev
    Next
    INDEX
    Explanations

    elements related to self-reflection and personal agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĨионнÑĭй
    -0.15
    obao
    -0.15
    iyah
    -0.14
    dle
    -0.14
    omite
    -0.14
    Insensitive
    -0.13
    Ñĩил
    -0.13
     ÑĥÑĤоÑĩ
    -0.13
    elib
    -0.13
    .openConnection
    -0.13
    POSITIVE LOGITS
     self
    0.73
    self
    0.64
     Self
    0.64
    -self
    0.61
     SELF
    0.60
    Self
    0.58
    SELF
    0.55
    _self
    0.54
    (self
    0.52
    	self
    0.51
    Activations Density 0.296%

    No Known Activations