INDEX

Explanations

references to locations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ONSE

-0.15

achel

-0.15

ãĥ¼ãĥŃ

-0.14

 Saunders

-0.14

ansson

-0.13

asca

-0.13

(valid

-0.13

hsi

-0.13

 mour

-0.13

iÃ¨re

-0.13

POSITIVE LOGITS

ic

0.15

Ð³Ð¾ÑĢÐ¾Ð´

0.14

æī§

0.14

olest

0.14

ikit

0.14

rale

0.14

 verst

0.13

SSIP

0.13

.tc

0.13

emento

0.13

Activations Density 0.748%

references to locations and institutions

No Comments

No Known Activations