INDEX

Explanations

symbols and punctuation 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

INFRINGEMENT

-0.16

 First

-0.14

erdings

-0.14

zl

-0.14

 Opera

-0.14

-Requested

-0.13

 With

-0.13

ìľłë¨¸

-0.13

One

-0.13

POSITIVE LOGITS

Nor

0.17

Que

0.16

Ed

0.16

vice

0.16

United

0.15

Ne

0.15

El

0.15

oland

0.15

èĳī

0.15

ina

0.15

Activations Density 0.231%

symbols and punctuation within the text

No Comments

No Known Activations