INDEX

Explanations

instances of significant actions or events occurring in 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

tdown

-0.15

aukee

-0.14

usalem

-0.14

.springboot

-0.14

leston

-0.14

Ð»Ñı

-0.14

igans

-0.14

overe

-0.14

.badlogic

-0.14

POSITIVE LOGITS

akk

0.15

 cheap

0.14

 Hunt

0.13

 Peterson

0.13

 http

0.13

WR

0.13

 Barr

0.13

abr

0.13

 seized

0.13

ACC

0.13

Activations Density 0.010%

instances of significant actions or events occurring in a narrative context

No Comments

No Known Activations