INDEX

Explanations

instances of the word "reference" and its variations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

strand

-0.18

erna

-0.16

tha

-0.16

_foreign

-0.15

ern

-0.15

la

-0.14

reich

-0.14

ForeignKey

-0.13

vide

-0.13

ish

-0.13

POSITIVE LOGITS

izes

0.22

ourcem

0.17

resher

0.16

idebar

0.16

andum

0.15

oÄį

0.15

/reference

0.15

ential

0.15

iÃ©n

0.15

yntax

0.14

Activations Density 0.035%

instances of the word "reference" and its variations in the text

No Comments

No Known Activations