INDEX

Explanations

comparisons or contrasts between two entities or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

swick

-0.15

hetto

-0.15

unik

-0.14

hus

-0.14

Ð²Ð°Ð´

-0.14

weed

-0.14

Ire

-0.13

adla

-0.13

coding

-0.13

_$_

-0.13

POSITIVE LOGITS

/of

0.19

raquo

0.15

/as

0.15

ï¸ı

0.15

eneration

0.14

/in

0.13

uong

0.13

ÑĶÐ¼

0.13

Activations Density 0.021%

comparisons or contrasts between two entities or subjects

No Comments

No Known Activations