INDEX

Explanations

negative sentiments or destructive patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 latter

-0.22

-sided

-0.17

-0.16

anja

-0.16

alt

-0.16

ing

-0.15

Tr

-0.15

le

-0.15

onde

-0.15

ÑģÐ°Ð¼

-0.15

POSITIVE LOGITS

webkit

0.15

ucas

0.14

ÑĢÐ¾Ð»

0.14

oro

0.14

ConverterFactory

0.14

 Roose

0.14

pio

0.14

InternalServerError

0.14

etwork

0.14

 wireType

0.14

Activations Density 0.066%

negative sentiments or destructive patterns

No Comments

No Known Activations