INDEX

Explanations

instances of the word "Read" and "Know," indicating a focus on reading content or acquiring knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

deg

-0.14

samp

-0.14

MediaType

-0.14

iju

-0.14

 Bucc

-0.13

 Cunning

-0.13

aya

-0.13

onn

-0.13

itness

-0.13

endi

-0.13

POSITIVE LOGITS

-caret

0.15

íĭĢ

0.14

atorium

0.13

imdi

0.13

tg

0.13

æµ¦

0.13

Jab

0.13

odash

0.13

lien

0.13

Activations Density 0.066%

instances of the word "Read" and "Know," indicating a focus on reading content or acquiring knowledge

No Comments

No Known Activations