INDEX

Explanations

references to specific locations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ¨ãĥ«

-0.14

ãģ£ãģ

-0.14

Ð¾ÑĤÑĥ

-0.14

Ø±ÙĬÙĥ

-0.14

UTDOWN

-0.13

Ð¾ÐºÑĥ

-0.13

sing

-0.13

zs

-0.13

enheim

-0.13

oire

-0.13

POSITIVE LOGITS

Fah

0.18

0.17

uld

0.15

ION

0.14

inu

0.14

kate

0.14

uze

0.14

uros

0.13

 Hlav

0.13

berman

0.13

Activations Density 0.247%

references to specific locations and institutions

No Comments

No Known Activations