INDEX

Explanations

references to companies and organizational structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.16

tes

-0.15

-0.14

zer

-0.14

oro

-0.14

ÑĨÐµÑĢ

-0.14

POSITIVE LOGITS

 effect

0.16

enberg

0.16

_effect

0.16

-effect

0.16

bbe

0.16

Unsafe

0.15

Ã³ng

0.15

unning

0.14

,eg

0.14

vang

0.14

Activations Density 0.006%

references to companies and organizational structures

No Comments

No Known Activations