INDEX

Explanations

references to completeness or thoroughness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ennes

-0.16

est

-0.16

off

-0.16

ez

-0.15

lm

-0.14

oil

-0.14

iff

-0.14

anz

-0.14

lenme

-0.14

POSITIVE LOGITS

/full

0.29

filled

0.22

-full

0.21

(full

0.19

full

0.19

stÃ¤nd

0.18

 full

0.18

IRCLE

0.17

-scale

0.17

ledged

0.17

Activations Density 0.047%

references to completeness or thoroughness

No Comments

No Known Activations