INDEX

Explanations

specific proper nouns or key terms that indicate notable entities or subjects

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

bsp

-0.17

isel

-0.17

ÑĢÑĥÑģ

-0.16

auc

-0.15

umper

-0.15

keh

-0.15

ersh

-0.15

ounters

-0.14

ungan

-0.14

ILE

-0.14

POSITIVE LOGITS

<<<

0.16

 æķħ

0.15

 hassle

0.14

hue

0.14

 cÃłng

0.14

alt

0.14

-Nazi

0.13

HING

0.13

Activations Density 0.008%

specific proper nouns or key terms that indicate notable entities or subjects

No Comments

No Known Activations