INDEX

Explanations

references to plugins, specifically in a software or technical context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ourn

-0.17

ted

-0.16

edin

-0.15

ingle

-0.15

Glo

-0.15

åĿĬ

-0.14

za

-0.14

áº±ng

-0.14

mit

-0.14

oggle

-0.14

POSITIVE LOGITS

/add

0.16

 Barnett

0.16

spark

0.15

iert

0.14

ToPoint

0.14

'gc

0.14

regunta

0.14

marsh

0.14

aire

0.14

ERA

0.14

Activations Density 0.056%

references to plugins, specifically in a software or technical context

No Comments

No Known Activations