INDEX

Explanations

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

eft

-0.15

 rendez

-0.14

 Wong

-0.13

)':

-0.13

rens

-0.13

omy

-0.13

 McGu

-0.13

 aside

-0.13

 Select

-0.13

Ã¡lo

-0.12

POSITIVE LOGITS

otec

0.16

uat

0.16

Peer

0.16

ismet

0.16

olet

0.15

Beam

0.15

itt

0.14

ØªÙĥ

0.14

quoise

0.14

Activations Density 0.127%

occurrences of the word "the."

No Comments

No Known Activations