INDEX

Explanations

occurrences of significant events or incidents in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

chio

-0.16

cher

-0.15

ÐµÑĤÐ¸

-0.15

erah

-0.15

\Bridge

-0.14

xo

-0.14

ä¸ĺ

-0.14

ibs

-0.14

ynn

-0.14

ylland

-0.13

POSITIVE LOGITS

 events

0.21

 happen

0.20

itious

0.18

uality

0.18

events

0.16

 aconte

0.16

/events

0.16

-events

0.16

 happening

0.15

Events

0.15

Activations Density 0.095%

occurrences of significant events or incidents in various contexts

No Known Activations