© 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. 1-LLAMASCOPE-RES-32K
    11. 2145
    Prev
    Next
    INDEX
    Explanations

    mentions of organized excursions or guided activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wald
    -0.16
     Charg
    -0.15
    pf
    -0.14
     Mu
    -0.14
    WO
    -0.14
    566
    -0.14
    imas
    -0.14
     Tom
    -0.14
    ingen
    -0.14
    TEMPLATE
    -0.13
    POSITIVE LOGITS
    åįĪ
    0.15
    .Annotation
    0.15
     Mellon
    0.14
    ORMAT
    0.14
     vel
    0.14
    ERSIST
    0.14
    itore
    0.13
    ecure
    0.13
    irthday
    0.13
    onec
    0.13
    Activations Density 0.002%

    No Known Activations