INDEX

Explanations

negative verb phrases related to functionality and performance issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

hub

-0.16

aster

-0.15

 Chill

-0.14

mast

-0.14

ìĬ¤íĭ°

-0.14

Hub

-0.14

ane

-0.14

-alist

-0.13

Hub

-0.13

.glide

-0.13

POSITIVE LOGITS

proper

0.17

 proper

0.16

 anymore

0.16

 Proper

0.16

é½

0.15

 seem

0.15

 properly

0.15

 seems

0.15

hower

0.14

 Seems

0.14

Activations Density 0.054%

negative verb phrases related to functionality and performance issues

No Comments

No Known Activations