© 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. 18-LLAMASCOPE-RES-32K
    11. 16648
    Prev
    Next
    INDEX
    Explanations

    references to specific events, characters, or elements within the Pokémon franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahoma
    -0.16
    Abstract
    -0.15
     Abstract
    -0.15
    rud
    -0.15
    .apple
    -0.14
    _TYP
    -0.14
    iks
    -0.14
    ceae
    -0.14
    enu
    -0.14
    RuntimeObject
    -0.14
    POSITIVE LOGITS
     Haj
    0.18
    .cg
    0.17
    Normalization
    0.17
    eps
    0.17
     seinen
    0.16
    æŁľ
    0.15
    Serialization
    0.15
     Moy
    0.15
    grave
    0.15
     Hin
    0.15
    Activations Density 0.094%

    No Known Activations