INDEX

Explanations

phrases that indicate a narrative or character interaction in storytelling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Ĥ¨

-0.16

itzer

-0.15

cia

-0.14

stro

-0.14

æ®¿

-0.14

ãģĶ

-0.14

_SCR

-0.14

 Ð¿ÑĢÐ¾Ñħ

-0.13

.Writer

-0.13

.bn

-0.13

POSITIVE LOGITS

 Fulton

0.15

 Crown

0.15

unn

0.15

pest

0.14

ÅĻich

0.14

 crown

0.14

ye

0.14

hos

0.14

imat

0.14

Activations Density 2.119%

phrases that indicate a narrative or character interaction in storytelling

No Comments

No Known Activations