INDEX

Explanations

phrases indicating an analysis or examination of beliefs and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

mÃŃ

-0.16

atar

-0.16

ÃŃky

-0.15

Offsets

-0.15

CTest

-0.15

ousel

-0.15

meli

-0.14

ieux

-0.14

IIIK

-0.14

 çĶŁåĳ½åĳ¨æľŁ

-0.14

POSITIVE LOGITS

holm

0.14

ius

0.14

gem

0.14

Tun

0.13

Gem

0.13

gem

0.13

Ung

0.13

Ú¯Ø§ÙĨÛĮ

0.13

Î·Î½

0.13

omens

0.13

Activations Density 0.002%

phrases indicating an analysis or examination of beliefs and actions

No Comments

No Known Activations