INDEX

Explanations

references to corporate headquarters and their location

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

atar

-0.15

å±¥

-0.15

ancer

-0.15

antha

-0.14

oder

-0.14

 anom

-0.14

RITE

-0.13

Ð²ÐµÑī

-0.13

ido

-0.13

Å¼e

-0.13

POSITIVE LOGITS

ctl

0.18

izzo

0.16

ajan

0.15

quare

0.15

hq

0.15

urdy

0.15

/head

0.15

à¸¯

0.15

Sharper

0.15

../../../

0.15

Activations Density 0.023%

references to corporate headquarters and their location

No Comments

No Known Activations