INDEX

Explanations

supportive phrases and expressions of opinion

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 konkrÃ©t

-0.15

sac

-0.15

ãģ°ãģĭãĤĬ

-0.14

_Application

-0.14

ingle

-0.14

UIS

-0.14

Tab

-0.13

unden

-0.13

asha

-0.13

 Commit

-0.13

POSITIVE LOGITS

getFullYear

0.14

latin

0.14

ãĥ³ãĥĲãĥ¼

0.14

osa

0.14

zik

0.14

 anale

0.13

ãĥķãĤ

0.13

.cons

0.13

èĥ

0.13

duk

0.13

Activations Density 0.489%

supportive phrases and expressions of opinion

No Comments

No Known Activations