INDEX

Explanations

negative sentiments and emotional expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ones

-0.16

Jay

-0.16

eland

-0.16

vy

-0.15

VS

-0.15

Gia

-0.15

vs

-0.14

ont

-0.14

vn

-0.14

ersen

-0.14

POSITIVE LOGITS

blink

0.15

uali

0.15

createQuery

0.15

[[]

0.14

-gnu

0.14

.GetLength

0.14

ÑĮÑİ

0.14

uppe

0.14

 blink

0.13

isu

0.13

Activations Density 0.374%

negative sentiments and emotional expressions

No Comments

No Known Activations