INDEX

Explanations

HTML tags and elements within the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ASSERT

-0.16

iera

-0.14

ë©

-0.14

 rele

-0.14

uilder

-0.13

ock

-0.13

iah

-0.13

 helf

-0.13

issement

-0.13

tab

-0.13

POSITIVE LOGITS

erd

0.14

deque

0.14

 ROLE

0.14

enstein

0.13

etag

0.13

èģ²

0.13

Ð¼Ð¾ÑĢ

0.13

etheus

0.13

ning

0.13

Activations Density 0.091%

HTML tags and elements within the document

No Comments

No Known Activations

HTML tags and elements within the document

No Comments

No Known Activations