INDEX

Explanations

phrases indicating proximity or distance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

sembly

-0.17

isci

-0.16

obot

-0.15

rowsers

-0.15

apiro

-0.15

à¤¿à¤¶à¤¤

-0.15

OLUMN

-0.15

.setPrototypeOf

-0.15

urtles

-0.15

@student

-0.14

POSITIVE LOGITS

 driving

0.15

 Driving

0.15

 bearer

0.15

oons

0.15

 forth

0.14

Fr

0.14

steps

0.14

 Brennan

0.14

Hab

0.14

Activations Density 0.041%

phrases indicating proximity or distance

No Comments

No Known Activations