INDEX

Explanations

references to the term "Mother."

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

-0.17

oger

-0.15

adir

-0.14

forced

-0.14

ITED

-0.14

nings

-0.14

ersh

-0.14

ÑĤÐ¸Ð¼

-0.14

ateur

-0.14

Î±Îº

-0.14

POSITIVE LOGITS

hood

0.15

etting

0.14

mrt

0.14

anlÄ±

0.14

campo

0.13

phies

0.13

arah

0.13

ÙĨÚ¯ÛĮ

0.13

ieces

0.13

ents

0.13

Activations Density 0.017%

references to the term "Mother."

No Comments

No Known Activations