INDEX

Explanations

instances of dialogue or conversation within a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

uisse

-0.16

uhl

-0.16

srd

-0.15

loh

-0.15

etag

-0.15

 nuest

-0.15

ajo

-0.15

Zd

-0.14

 essentially

-0.14

owell

-0.14

POSITIVE LOGITS

 narr

0.20

ask

0.17

ask

0.17

 Majesty

0.17

 quar

0.17

 asking

0.16

fetch

0.16

pac

0.16

 convers

0.16

 asked

0.16

Activations Density 0.681%

instances of dialogue or conversation within a narrative

No Comments

No Known Activations