INDEX

Explanations

references to "boy" or related concepts within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

lec

-0.17

onica

-0.17

eer

-0.17

Ð¼Ð¾Ð²

-0.16

lek

-0.16

edi

-0.16

leck

-0.16

lej

-0.16

Ð¸ÑĤÐ¸

-0.16

anter

-0.16

POSITIVE LOGITS

hood

0.25

/man

0.24

friends

0.24

friend

0.22

-girl

0.20

oyo

0.19

ish

0.19

nton

0.19

/g

0.18

ishly

0.18

Activations Density 0.026%

references to "boy" or related concepts within the text

No Comments

No Known Activations