INDEX

Explanations

instances of references to changes or modifications 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 @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

pa

-0.17

anga

-0.16

 cruc

-0.15

ants

-0.15

ROS

-0.15

Hugh

-0.14

_ros

-0.14

Ð²Ð¸ÑĤ

-0.14

 Wilhelm

-0.14

ÏĢÎ»

-0.14

POSITIVE LOGITS

itom

0.15

amient

0.15

Ø§Øµ

0.15

edback

0.15

uo

0.14

ooth

0.14

olas

0.14

.setTo

0.14

iali

0.14

To

0.14

Activations Density 0.021%

instances of references to changes or modifications in various contexts

No Comments

No Known Activations