INDEX

Explanations

statements and remarks made by individuals in a formal context

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

ool

-0.15

 Mang

-0.14

 Dash

-0.14

lobals

-0.14

 tast

-0.13

ansen

-0.13

áº¿n

-0.13

uel

-0.13

iel

-0.13

POSITIVE LOGITS

onso

0.19

ibi

0.17

.scalablytyped

0.15

KNOWN

0.15

usk

0.15

WebHost

0.14

achu

0.14

UBLE

0.14

ÎµÏģ

0.13

izza

0.13

Activations Density 0.049%

statements and remarks made by individuals in a formal context

No Comments

No Known Activations