INDEX

Explanations

references to the Himalayas and related geographical features

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

 Bass

-0.14

iras

-0.14

 Pron

-0.14

tick

-0.14

oho

-0.14

 humour

-0.13

rome

-0.13

Pes

-0.13

inch

-0.13

POSITIVE LOGITS

º¼

0.16

ugs

0.15

 Neighborhood

0.15

utow

0.15

ÅĽÄĩ

0.14

è½½

0.14

SCO

0.14

ç¹ģ

0.14

 Clintons

0.14

allon

0.14

Activations Density 0.002%

references to the Himalayas and related geographical features

No Comments

No Known Activations