INDEX

Explanations

terms related to extension or expansion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

#af

-0.17

OperationException

-0.16

swing

-0.15

.gdx

-0.15

eyed

-0.15

();)

-0.15

/ay

-0.15

thag

-0.15

erce

-0.14

Æ¡m

-0.14

POSITIVE LOGITS

ene

0.17

ë°Ģ

0.16

ention

0.16

ensive

0.15

(extension

0.15

ential

0.15

ede

0.15

ocrine

0.15

ordinary

0.14

reach

0.14

Activations Density 0.052%

terms related to extension or expansion

No Comments

No Known Activations