INDEX

Explanations

references to confusion or identity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

-0.17

reed

-0.17

egg

-0.16

èĢ

-0.16

(*)(

-0.15

ographic

-0.15

Gir

-0.15

ellan

-0.14

zon

-0.14

 actionTypes

-0.14

POSITIVE LOGITS

.managed

0.17

 Fitz

0.15

bler

0.14

âĺĨ

0.14

IVES

0.14

_inventory

0.14

athy

0.14

OF

0.14

ictory

0.14

Î»Î¿Î¹

0.13

Activations Density 0.001%

references to confusion or identity in various contexts

No Comments

No Known Activations