INDEX

Explanations

contrasts and contradictions in experiences

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

iesz

-0.17

anos

-0.15

OSH

-0.15

annis

-0.15

osh

-0.14

ier

-0.14

ifr

-0.13

ana

-0.13

ellan

-0.13

itt

-0.13

POSITIVE LOGITS

 overall

0.15

eker

0.15

çĶļ

0.15

 Tits

0.15

éľŀ

0.15

 Overall

0.14

Gri

0.14

cors

0.14

 budgets

0.14

ÑĢÐ°ÑģÑĤÐ°

0.14

Activations Density 0.101%

contrasts and contradictions in experiences

No Known Activations