© 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. 19-LLAMASCOPE-RES-32K
    11. 30686
    Prev
    Next
    INDEX
    Explanations

    code-related elements and structures, particularly those involving hash functions and object equality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bsolute
    -0.17
    (Cs
    -0.15
    igham
    -0.15
    incinn
    -0.14
    vsp
    -0.14
    ÑĢаж
    -0.14
     Kelvin
    -0.14
    ingroup
    -0.14
    adel
    -0.14
     compet
    -0.14
    POSITIVE LOGITS
    .hashCode
    0.28
    hashCode
    0.27
    .GetHashCode
    0.23
     hashCode
    0.22
    HashCode
    0.21
     hash
    0.20
    sey
    0.18
     hashing
    0.18
     Hash
    0.18
     hasher
    0.17
    Activations Density 0.029%

    No Known Activations