INDEX

Explanations

occurrences of the word "Cord" and its variations within 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

berman

-0.16

eyed

-0.16

isor

-0.16

irut

-0.15

bourg

-0.15

usercontent

-0.15

istics

-0.15

Subviews

-0.14

erties

-0.14

 warrant

-0.14

POSITIVE LOGITS

oba

0.21

ovan

0.21

ially

0.19

cord

0.19

age

0.18

uro

0.18

oning

0.17

oned

0.17

elia

0.16

antly

0.15

Activations Density 0.009%

occurrences of the word "Cord" and its variations within the text

No Comments

No Known Activations