INDEX

Explanations

occurrences of the word "in."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

case

-0.16

aha

-0.16

 fountain

-0.15

arrow

-0.15

avn

-0.15

ala

-0.15

up

-0.15

com

-0.14

 detriment

-0.14

POSITIVE LOGITS

ozor

0.17

elik

0.17

 Action

0.16

plode

0.16

rane

0.16

 action

0.16

RuleContext

0.15

unsch

0.15

deniz

0.14

Action

0.14

Activations Density 0.191%

occurrences of the word "in."

No Comments

No Known Activations