INDEX

Explanations

names and titles of individuals within organizational contexts

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

ales

-0.17

acher

-0.15

nell

-0.15

eter

-0.15

yme

-0.14

ãĤ¦ãĥĪ

-0.14

alian

-0.14

plib

-0.13

umbs

-0.13

unched

-0.13

POSITIVE LOGITS

hower

0.17

NotFoundException

0.16

äºĭ

0.16

èĬ³

0.15

oba

0.15

==>

0.14

ippy

0.13

ROOT

0.13

uye

0.13

 vocab

0.13

Activations Density 0.246%

names and titles of individuals within organizational contexts

No Comments

No Known Activations