INDEX

Explanations

the article "A"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

lu

-0.18

la

-0.18

le

-0.17

ns

-0.17

ose

-0.16

otti

-0.16

pper

-0.16

st

-0.16

ling

-0.15

ces

-0.15

POSITIVE LOGITS

idth

0.19

aft

0.18

GenerationStrategy

0.16

ufe

0.15

etten

0.15

Å¡ker

0.15

elian

0.15

reff

0.15

ections

0.15

chalk

0.15

Activations Density 0.154%

the article "A"

No Comments

No Known Activations