INDEX

Explanations

statements of personal opinion or sentiment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ç·

-0.17

@student

-0.16

 confess

-0.15

ONSE

-0.15

Î´Î¬

-0.14

TestFixture

-0.14

-gun

-0.14

 confessed

-0.14

bum

-0.14

quire

-0.14

POSITIVE LOGITS

 wonder

0.25

 Wonder

0.20

 wonders

0.18

 expected

0.17

chal

0.17

Wonder

0.16

 Agree

0.16

 lived

0.16

 fail

0.16

 sick

0.15

Activations Density 0.181%

statements of personal opinion or sentiment

No Comments

No Known Activations