INDEX

Explanations

instances of the word "blog" and related terms and phrases

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

urses

-0.17

lings

-0.15

eous

-0.14

 toll

-0.14

LATED

-0.14

ursed

-0.14

inel

-0.14

ekli

-0.14

cosa

-0.14

ezi

-0.14

POSITIVE LOGITS

azon

0.18

warts

0.16

arith

0.16

 Gast

0.15

spot

0.15

athon

0.15

lio

0.14

/video

0.14

cdecl

0.14

/twitter

0.14

Activations Density 0.022%

instances of the word "blog" and related terms and phrases

No Comments

No Known Activations