© 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. 22-LLAMASCOPE-RES-32K
    6. 28587
    Prev
    Next
    INDEX
    Explanations

    negations or phrases that indicate the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anych
    -0.17
    Äħd
    -0.15
    uso
    -0.15
    оÑĥ
    -0.15
    uj
    -0.15
    ga
    -0.14
    anni
    -0.14
    ntp
    -0.14
     Kou
    -0.14
    roid
    -0.14
    POSITIVE LOGITS
     matter
    0.34
     wonder
    0.27
    matter
    0.26
     Matter
    0.23
     doubt
    0.21
     one
    0.21
    strand
    0.20
     amount
    0.19
     sooner
    0.18
     surprise
    0.18
    Activations Density 0.045%

    No Known Activations