© 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. 24-LLAMASCOPE-RES-32K
    11. 21282
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of personal opinions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erval
    -0.17
    oun
    -0.15
    ouz
    -0.15
    eniable
    -0.14
    adden
    -0.14
    osaur
    -0.14
    ously
    -0.14
     Král
    -0.13
    uin
    -0.13
    anel
    -0.13
    POSITIVE LOGITS
     who
    0.31
    who
    0.28
     beg
    0.23
     Who
    0.22
    Who
    0.21
     shr
    0.20
     Meh
    0.20
     shrugged
    0.19
     qui
    0.19
     thems
    0.18
    Activations Density 0.221%

    No Known Activations