INDEX

Explanations

phrases that indicate comparisons or quantifications involving "as" and "little."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

igy

-0.15

 Boeh

-0.15

eah

-0.14

ekim

-0.14

Ã£o

-0.14

 dedi

-0.14

tring

-0.14

 biáº¿n

-0.14

dress

-0.14

avo

-0.14

POSITIVE LOGITS

 Plains

0.15

zn

0.15

Hel

0.14

 tissue

0.14

hel

0.14

 instant

0.14

sw

0.13

onna

0.13

CELER

0.13

Activations Density 0.018%

phrases that indicate comparisons or quantifications involving "as" and "little."

No Comments

No Known Activations