INDEX

Explanations

references to specific locations, particularly cities and landmarks

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

ils

-0.16

:CGRect

-0.15

á»įn

-0.15

 assist

-0.14

teil

-0.14

bau

-0.14

æ¦ľ

-0.14

/Common

-0.14

 Bain

-0.14

umlu

-0.14

POSITIVE LOGITS

uing

0.18

antz

0.17

amic

0.16

rael

0.15

hm

0.15

UED

0.15

aque

0.15

erie

0.15

Ð¾Ð²ÑĭÐµ

0.15

ing

0.14

Activations Density 0.021%

references to specific locations, particularly cities and landmarks

No Comments

No Known Activations