INDEX

Explanations

occurrences of the word "total" related to quantifying or summarizing information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

es

-0.15

 Wich

-0.15

 bump

-0.15

olla

-0.14

link

-0.14

ez

-0.14

Ã¤ge

-0.14

 thá»©c

-0.14

handling

-0.14

RAY

-0.14

POSITIVE LOGITS

led

0.21

itarian

0.18

izing

0.17

LED

0.17

ingham

0.17

izador

0.17

istic

0.16

itaire

0.16

izer

0.15

izers

0.15

Activations Density 0.028%

occurrences of the word "total" related to quantifying or summarizing information

No Comments

No Known Activations