INDEX

Explanations

negations or phrases indicating the absence of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ults

-0.17

Peace

-0.15

 mant

-0.15

leyin

-0.14

uy

-0.14

 Word

-0.14

olas

-0.14

astr

-0.14

 Mant

-0.14

COPE

-0.13

POSITIVE LOGITS

ori

0.19

abyrin

0.17

 Disp

0.16

 ÄĮer

0.15

epad

0.15

ullan

0.15

 Morg

0.14

pov

0.14

.updateDynamic

0.13

adiens

0.13

Activations Density 0.043%

negations or phrases indicating the absence of something

No Comments

No Known Activations