INDEX

Explanations

references to specific organizations or locations, particularly those related to "NC" or North Carolina

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

lou

-0.18

kou

-0.17

utt

-0.17

othy

-0.16

 Crest

-0.16

-0.15

ka

-0.15

amak

-0.15

adro

-0.14

GT

-0.14

POSITIVE LOGITS

imb

0.17

elles

0.17

 State

0.17

NC

0.16

(nc

0.16

nc

0.15

urses

0.15

leme

0.15

.nlm

0.15

lej

0.15

Activations Density 0.019%

references to specific organizations or locations, particularly those related to "NC" or North Carolina

No Comments

No Known Activations