© 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. 27-LLAMASCOPE-RES-32K
    11. 19548
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aurant
    -0.17
     nutshell
    -0.16
     cui
    -0.16
     Sense
    -0.15
    sofar
    -0.15
    onu
    -0.15
    ninger
    -0.14
    stood
    -0.14
    ISMATCH
    -0.14
    vented
    -0.13
    POSITIVE LOGITS
     concert
    0.24
     lock
    0.22
     dro
    0.21
    -step
    0.18
     step
    0.18
     stages
    0.18
     ern
    0.17
     fits
    0.17
     turn
    0.17
     sync
    0.17
    Activations Density 0.155%

    No Known Activations