INDEX

Explanations

proper nouns and specific names mentioned in 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Rogers

-0.15

çķ

-0.15

.Bus

-0.14

uilder

-0.14

æĭĶ

-0.14

anel

-0.13

ØªÙĬ

-0.13

 mind

-0.13

ROC

-0.13

znik

-0.13

POSITIVE LOGITS

apol

0.17

etto

0.16

aska

0.16

uche

0.16

ule

0.16

ocaly

0.15

0.14

apor

0.14

ettel

0.14

iers

0.14

Activations Density 0.000%

proper nouns and specific names mentioned in the text

No Comments

No Known Activations