INDEX

Explanations

references to location and contextual descriptors related to places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

conds

-0.20

inals

-0.17

 ping

-0.14

pic

-0.14

ï¸

-0.14

ri

-0.14

 cave

-0.14

ickness

-0.14

ough

-0.14

POSITIVE LOGITS

ernes

0.16

.xtext

0.16

rud

0.15

prung

0.15

ION

0.15

ensen

0.14

iones

0.14

 hare

0.14

thane

0.14

Ð»ÑĥÑĪ

0.14

Activations Density 0.130%

references to location and contextual descriptors related to places

No Comments

No Known Activations