INDEX

Explanations

terminology related to relocation and movement processes

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

 yana

-0.15

arius

-0.15

tha

-0.15

ÛĮØ§ÙĨ

-0.14

quo

-0.14

AMI

-0.14

opers

-0.13

ahoma

-0.13

REA

-0.13

ustum

-0.13

POSITIVE LOGITS

ings

0.16

avy

0.16

InProgress

0.15

ISTA

0.15

uÃ©

0.14

combe

0.14

erset

0.14

tings

0.14

Latch

0.14

able

0.14

Activations Density 0.686%

terminology related to relocation and movement processes

No Comments

No Known Activations