INDEX

Explanations

instructions or indicators that present information in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Ballard

-0.16

anches

-0.15

anto

-0.15

atters

-0.15

 Pearson

-0.14

Ð¸Ñģ

-0.14

 Hale

-0.14

eres

-0.13

Pear

-0.13

POSITIVE LOGITS

 below

0.23

below

0.20

 table

0.20

 Ð½Ð¸Ð¶Ðµ

0.19

Below

0.18

 Below

0.17

 abaixo

0.16

æĺ¯æĪĳ

0.16

 BELOW

0.15

.criteria

0.15

Activations Density 0.050%

instructions or indicators that present information in a structured format

No Comments

No Known Activations