INDEX

Explanations

navigation elements in a web document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 disp

-0.16

hea

-0.15

ent

-0.15

ongyang

-0.14

ãĢģ

-0.14

ulty

-0.14

ech

-0.14

un

-0.14

ollo

-0.13

avia

-0.13

POSITIVE LOGITS

eneg

0.17

anzi

0.17

istrovstvÃŃ

0.17

Å¡ek

0.16

áº¿p

0.15

DEX

0.15

 addCriterion

0.15

ovÃŃ

0.15

anford

0.14

ãĥ³ãĥĳ

0.14

Activations Density 0.014%

navigation elements in a web document

No Comments

No Known Activations

navigation elements in a web document

No Comments

No Known Activations