INDEX

Explanations

references to product features and comparisons

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

essler

-0.15

_EFFECT

-0.15

uchos

-0.14

.createFrom

-0.14

zw

-0.14

 commissioned

-0.14

ialog

-0.14

abal

-0.14

/System

-0.13

ellas

-0.13

POSITIVE LOGITS

undra

0.17

mlin

0.16

anja

0.16

.wr

0.15

 Kahn

0.14

imler

0.14

 Bolt

0.14

ahren

0.14

urer

0.14

OFF

0.14

Activations Density 0.022%

references to product features and comparisons

No Comments

No Known Activations