INDEX

Explanations

references to specific geographical locations, particularly cities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

âĢ¦↵↵↵

-0.18

Dra

-0.16

dra

-0.15

sched

-0.15

vou

-0.15

Mocks

-0.15

Å¾el

-0.15

zel

-0.15

.UnitTesting

-0.14

agos

-0.14

POSITIVE LOGITS

iana

0.16

anca

0.15

ussen

0.15

 Genuine

0.15

ãģķãģ¾

0.14

igid

0.14

ois

0.14

lund

0.14

 Hancock

0.14

burn

0.14

Activations Density 0.002%

references to specific geographical locations, particularly cities

No Comments

No Known Activations