INDEX

Explanations

references to keyboards and typing activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Lone

-0.16

eree

-0.15

heck

-0.15

emento

-0.15

isor

-0.15

ookies

-0.14

 prof

-0.14

 appointment

-0.14

æģ¯

-0.14

jedn

-0.14

POSITIVE LOGITS

urrect

0.15

errat

0.15

ìĹĶ

0.15

Spacer

0.14

ansen

0.14

_FRAMEBUFFER

0.14

 Dispose

0.13

ermal

0.13

-Mail

0.13

bbe

0.13

Activations Density 0.018%

references to keyboards and typing activities

No Comments

No Known Activations