INDEX

Explanations

phrases that indicate skepticism or contradiction regarding official statements and policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Ab

-0.15

 private

-0.15

XC

-0.15

 Replies

-0.15

lescope

-0.14

 Newman

-0.14

.tp

-0.13

DebugEnabled

-0.13

aylor

-0.13

POSITIVE LOGITS

ffen

0.17

ometry

0.16

ucer

0.15

gel

0.15

oner

0.15

=key

0.15

ucher

0.14

ÛĮÙĨÙĩ

0.14

aukee

0.14

quila

0.14

Activations Density 0.218%

phrases that indicate skepticism or contradiction regarding official statements and policies

No Comments

No Known Activations