INDEX

Explanations

sequences indicating the passage of time and events in a narrative

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

aggio

-0.17

ouro

-0.16

à¤łà¤¨

-0.15

ÏģÎ¬

-0.14

 recently

-0.14

íĻķ

-0.14

imoto

-0.14

yon

-0.14

æµ¦

-0.13

imed

-0.13

POSITIVE LOGITS

 soon

0.17

 Soon

0.16

ModelError

0.16

 prest

0.16

vo

0.16

RLF

0.15

 estar

0.15

 rough

0.14

rud

0.14

Soon

0.14

Activations Density 0.159%

sequences indicating the passage of time and events in a narrative

No Known Activations