INDEX

Explanations

comparisons and evaluations related to value and needs in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

emsp

-0.19

ozy

-0.17

_ips

-0.15

Ãºa

-0.15

iky

-0.15

ulumi

-0.14

 billeder

-0.14

ocator

-0.14

Ð°Ð½ÑģÐ¸

-0.14

Sharper

-0.14

POSITIVE LOGITS

 different

0.21

 differently

0.19

 another

0.18

 khÃ¡c

0.18

 diferente

0.18

different

0.17

 next

0.16

 differs

0.16

 differed

0.16

next

0.15

Activations Density 0.106%

comparisons and evaluations related to value and needs in various contexts

No Comments

No Known Activations