INDEX

Explanations

references to locations or places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Dst

-0.16

 unut

-0.15

gmt

-0.15

à¹īà¸Ń

-0.14

icip

-0.14

ErrorException

-0.14

Rim

-0.14

ahoma

-0.14

gregator

-0.14

idth

-0.13

POSITIVE LOGITS

 downtown

0.17

 Branch

0.15

Suc

0.14

ipar

0.14

 Downtown

0.14

 Suit

0.14

 Feld

0.14

su

0.13

peg

0.13

xec

0.13

Activations Density 0.123%

references to locations or places

No Comments

No Known Activations