INDEX

Explanations

phrases related to mounting or attaching objects

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

nels

-0.15

empo

-0.15

uty

-0.15

ulers

-0.15

-0.14

nob

-0.14

anning

-0.14

 Chatt

-0.14

 Franc

-0.14

usi

-0.14

POSITIVE LOGITS

 Kens

0.20

aroo

0.18

ideographic

0.17

 quad

0.15

PILE

0.15

rophic

0.14

uggle

0.14

anh

0.14

ividual

0.14

isco

0.14

Activations Density 0.009%

phrases related to mounting or attaching objects

No Comments

No Known Activations