INDEX

Explanations

HTML or web-related tag structures and references to APIs and their components

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

ãĤ¤ãĥĦ

-0.16

IONS

-0.16

yu

-0.16

ingers

-0.15

orris

-0.15

ologne

-0.15

issen

-0.15

ions

-0.14

Äĥn

-0.14

ruba

-0.14

POSITIVE LOGITS

atl

0.15

DCALL

0.14

Tem

0.14

Nev

0.13

ENC

0.13

 Ø§ÙĦÙħØ¤

0.13

ëĵĿ

0.13

 Edwin

0.13

ãģ£ãģį

0.13

Activations Density 0.063%

HTML or web-related tag structures and references to APIs and their components

No Comments

No Known Activations