INDEX

Explanations

words related to expressing dissatisfaction or grievances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

let

-0.18

Ø®Ø§ÙĨÙĩ

-0.15

anio

-0.15

_CAPACITY

-0.14

\<^

-0.14

 Lent

-0.14

wes

-0.14

ainter

-0.14

ANE

-0.14

ablo

-0.13

POSITIVE LOGITS

addon

0.16

ewood

0.16

ocol

0.15

 chung

0.14

arel

0.14

lyn

0.14

Ð¾Ð¼ÐµÑĢ

0.14

ude

0.14

à¤ľà¤°

0.14

 Cannon

0.14

Activations Density 0.031%

words related to expressing dissatisfaction or grievances

No Comments

No Known Activations