INDEX

Explanations

instances of the word "by" indicating authorship or attribution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

aina

-0.17

sti

-0.16

wake

-0.16

 Pale

-0.15

 Palm

-0.15

chet

-0.15

lena

-0.15

vale

-0.14

venes

-0.14

eyn

-0.14

POSITIVE LOGITS

kyt

0.14

 Spark

0.14

ÑĸÑĪ

0.14

Æł

0.14

SearchTree

0.14

_docs

0.14

 nÃ³ng

0.14

ault

0.14

ISR

0.13

 lÃªn

0.13

Activations Density 0.005%

instances of the word "by" indicating authorship or attribution

No Comments

No Known Activations