INDEX

Explanations

references to specific events, quantities, or time frames in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

loor

-0.15

.internet

-0.15

front

-0.15

ÑĤÐµÐ½

-0.15

ront

-0.14

 forg

-0.14

ObjectOfType

-0.14

_FRONT

-0.14

 Front

-0.14

å½¢å¼ı

-0.14

POSITIVE LOGITS

avras

0.17

 partition

0.17

0.16

Partition

0.16

 Partition

0.16

 separation

0.15

 partitions

0.14

åĽ´

0.14

 Retreat

0.14

odia

0.14

Activations Density 0.030%

references to specific events, quantities, or time frames in text

No Comments

No Known Activations