INDEX

Explanations

connections and relationships among ideas within a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Impossible

-0.15

à¥Įà¤Ł

-0.15

eniable

-0.15

ginas

-0.15

 deflate

-0.14

/Table

-0.14

 Impossible

-0.14

anas

-0.14

edith

-0.14

 imposs

-0.13

POSITIVE LOGITS

 Works

0.22

 works

0.21

 worked

0.21

 proved

0.20

 satisfactory

0.19

 suff

0.18

Works

0.18

works

0.17

 adequate

0.17

 seemed

0.16

Activations Density 0.097%

connections and relationships among ideas within a narrative context

No Comments

No Known Activations