INDEX

Explanations

references to locations, particularly cities and geographical areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

berger

-0.15

Eg

-0.15

à¤Ĥà¤ľ

-0.15

lico

-0.15

rack

-0.15

 Dien

-0.14

eg

-0.14

cess

-0.14

aceous

-0.14

POSITIVE LOGITS

.scalablytyped

0.18

ohl

0.17

ville

0.17

VILLE

0.16

 æ©

0.16

@student

0.16

iens

0.15

astle

0.15

 jadx

0.15

exter

0.15

Activations Density 0.057%

references to locations, particularly cities and geographical areas

No Comments

No Known Activations