INDEX

Explanations

the presence of articles and the word "ent."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

©

-0.17

nbsp

-0.16

arden

-0.15

vil

-0.15

uentes

-0.15

à¸İ

-0.15

 ApiException

-0.14

lops

-0.14

/System

-0.14

POSITIVE LOGITS

Ø¯Ø§Ø¯

0.16

pos

0.15

gue

0.15

ote

0.15

pcf

0.15

leyin

0.15

het

0.14

Peer

0.14

jen

0.14

çĽ®

0.14

Activations Density 0.002%

the presence of articles and the word "ent."

No Comments

No Known Activations