© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 59492
    Prev
    Next
    INDEX
    Explanations

    terms related to marketing strategies and targeting techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erap
    -0.07
     Güven
    -0.07
    rov
    -0.07
    tera
    -0.07
    tero
    -0.07
    layan
    -0.07
    ocol
    -0.07
    OTAL
    -0.07
    μοÏħ
    -0.06
    λεÏħ
    -0.06
    POSITIVE LOGITS
     targeting
    0.12
     Target
    0.10
     target
    0.10
    target
    0.10
    Target
    0.09
    _target
    0.09
     targeted
    0.08
     targets
    0.08
    -target
    0.08
     ad
    0.08
    Activations Density 0.001%

    No Known Activations