INDEX

Explanations

pronouns that refer to objects or subjects in the narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

wet

-0.15

elsey

-0.15

TEMPL

-0.14

ÐºÑĥ

-0.14

OLON

-0.14

 LIABLE

-0.14

ugen

-0.14

chema

-0.14

 Eisen

-0.14

POSITIVE LOGITS

Å¡tÄĽ

0.16

iner

0.15

udy

0.15

íı¬

0.15

esser

0.15

idar

0.14

StackNavigator

0.14

itrust

0.13

anner

0.13

ÑĨÐ¸Ð½

0.13

Activations Density 0.331%

pronouns that refer to objects or subjects in the narrative

No Comments

No Known Activations