INDEX

Explanations

references to specific individuals in a relational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

HING

-0.18

-0.16

Äįer

-0.15

resher

-0.15

orent

-0.14

eyer

-0.14

olle

-0.14

rij

-0.14

phia

-0.14

lla

-0.14

POSITIVE LOGITS

holm

0.14

à¹ģà¸£à¸ģ

0.14

.Zero

0.13

.ef

0.13

 forCell

0.13

á»Ŀ

0.13

ormap

0.13

Ø±ÙĪØ·

0.13

iners

0.13

WF

0.13

Activations Density 0.267%

references to specific individuals in a relational context

No Comments

No Known Activations