INDEX

Explanations

actions and interactions among characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

boBox

-0.16

Å¡t

-0.15

Enlarge

-0.14

åĶĩ

-0.14

IVAL

-0.14

tsy

-0.14

æĥħ

-0.14

dzi

-0.14

tube

-0.13

POSITIVE LOGITS

amy

0.17

imple

0.16

andler

0.15

heads

0.15

ople

0.14

 himself

0.14

 Cycle

0.14

ycle

0.14

occo

0.14

amu

0.14

Activations Density 2.235%

actions and interactions among characters

No Comments

No Known Activations