INDEX

Explanations

phrases that indicate recommendations and reviews of experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

utor

-0.18

ÑĢÐµÐ±

-0.17

brig

-0.16

 Ston

-0.15

eger

-0.15

FP

-0.15

ahead

-0.14

 storm

-0.14

rax

-0.14

POSITIVE LOGITS

ĥ

0.16

 knull

0.16

ayne

0.16

ylinder

0.15

Î¼Î¬

0.15

ognito

0.14

PHA

0.14

yme

0.14

 worth

0.14

 Tape

0.14

Activations Density 0.336%

phrases that indicate recommendations and reviews of experiences

No Comments

No Known Activations