INDEX

Explanations

references to programming and user interface elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

loat

-0.21

mons

-0.19

ambi

-0.18

lags

-0.16

cdecl

-0.16

dued

-0.15

uer

-0.15

Sel

-0.15

aira

-0.14

lagen

-0.14

POSITIVE LOGITS

ongoose

0.16

ëĳ¥

0.15

 Bradley

0.15

BCM

0.15

elm

0.14

kea

0.14

Activations Density 0.120%

references to programming and user interface elements

No Comments

No Known Activations