INDEX

Explanations

associations with scientific and technical terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Driver

-0.16

Driver

-0.15

ncia

-0.14

ISO

-0.14

.Driver

-0.14

emu

-0.14

 alike

-0.14

*(*

-0.14

_story

-0.14

Hoy

-0.13

POSITIVE LOGITS

ìķħ

0.17

aeper

0.16

 Gerr

0.16

ÙĪØ«

0.15

ãĥ³ãĥķ

0.15

 Pied

0.14

åĳ

0.14

illi

0.14

 Mart

0.14

bstract

0.14

Activations Density 0.252%

associations with scientific and technical terminology

No Comments

No Known Activations