INDEX

Explanations

mentions of the word "Red" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.17

abilities

-0.16

omatic

-0.16

Ã¼rk

-0.16

unw

-0.15

anger

-0.15

atics

-0.15

astro

-0.14

à¤ł

-0.14

eties

-0.14

POSITIVE LOGITS

ults

0.17

ucing

0.16

uces

0.15

mond

0.15

dish

0.15

ARRANT

0.15

ither

0.15

emption

0.15

Activations Density 0.024%

mentions of the word "Red" in various contexts

No Comments

No Known Activations