INDEX

Explanations

copyright dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

sets

-0.16

actively

-0.16

hm

-0.15

er

-0.15

agna

-0.14

sWith

-0.14

ouri

-0.14

inger

-0.14

gt

-0.14

POSITIVE LOGITS

emiz

0.16

 nouvel

0.16

Tem

0.15

 Temper

0.15

eci

0.15

 temper

0.14

 Temperature

0.14

.::

0.14

æ´¾

0.14

 temperature

0.14

Activations Density 0.010%

copyright dates

No Comments

No Known Activations