INDEX

Explanations

structured data related to attributes and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

éĻ£

-0.17

imli

-0.16

untas

-0.15

ÏĦÏĥ

-0.15

éĺµ

-0.14

erus

-0.14

eri

-0.14

oras

-0.14

RIC

-0.13

POSITIVE LOGITS

ÃŃnÄĽ

0.13

Din

0.13

ÃĹ↵↵

0.13

enderit

0.13

uba

0.13

 Dict

0.13

.Cmd

0.12

 Bars

0.12

incinn

0.12

ÑĢÑı

0.12

Activations Density 0.056%

structured data related to attributes and classifications

No Comments

No Known Activations