INDEX

Explanations

instructions related to omitting or excluding elements

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

ibble

-0.16

bid

-0.15

uly

-0.15

hiro

-0.15

ERA

-0.15

akh

-0.14

 Yates

-0.14

ersen

-0.14

 coinc

-0.14

berger

-0.13

POSITIVE LOGITS

0.16

 Shuttle

0.15

Jesus

0.15

orio

0.15

.obtain

0.14

 geil

0.14

 Jesus

0.14

ÐµÐµ

0.14

wdx

0.14

Activations Density 0.043%

instructions related to omitting or excluding elements

No Comments

No Known Activations