INDEX

Explanations

references to military alliances and coordinated operations

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

-fontawesome

-0.15

ĵĺ

-0.14

 Policy

-0.14

UDIO

-0.14

Ð°ÑĤÑĥ

-0.14

 Strap

-0.14

skirts

-0.13

!!!!↵↵

-0.13

ÐµÐºÑĤÐ¾ÑĢ

-0.13

POSITIVE LOGITS

wh

0.16

 Shar

0.15

 fund

0.15

Dah

0.15

ene

0.14

auen

0.14

DA

0.14

Ã¶m

0.14

ANTE

0.14

 Graf

0.14

Activations Density 0.423%

references to military alliances and coordinated operations

No Comments

No Known Activations