INDEX

Explanations

instances of the word "reason" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

cat

-0.15

gow

-0.14

 keyed

-0.14

kir

-0.14

 Margin

-0.14

uye

-0.14

omp

-0.13

aur

-0.13

/run

-0.13

gia

-0.13

POSITIVE LOGITS

why

0.22

why

0.19

 dolayÄ±

0.16

nant

0.16

nal

0.16

upert

0.16

lessly

0.16

EO

0.16

Ã¼stÃ¼

0.16

WHY

0.15

Activations Density 0.032%

instances of the word "reason" and its variations

No Comments

No Known Activations