INDEX

Explanations

numerical values related to percentages and measurements in a technical context

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

affen

-0.18

ajar

-0.18

ulen

-0.17

ulty

-0.17

ajas

-0.16

áºŃy

-0.16

_scheme

-0.15

Î´Î®

-0.15

ledo

-0.15

inery

-0.15

POSITIVE LOGITS

udi

0.17

 credit

0.15

erman

0.15

ior

0.15

urt

0.14

zm

0.14

ki

0.14

Activations Density 0.002%

numerical values related to percentages and measurements in a technical context

No Comments

No Known Activations