INDEX

Explanations

instances of the word "which" or variations thereof

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

idis

-0.16

ilater

-0.15

eniable

-0.15

that

-0.15

utes

-0.14

ationally

-0.14

utos

-0.14

indh

-0.14

ungeons

-0.14

arkin

-0.13

POSITIVE LOGITS

is

0.23

 considering

0.23

 means

0.21

 explains

0.20

 Considering

0.18

Considering

0.18

_means

0.17

means

0.17

0.16

soever

0.16

Activations Density 0.094%

instances of the word "which" or variations thereof

No Comments

No Known Activations