INDEX

Explanations

names of people and associated information

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 [âĢ¦]↵↵

-0.14

ichel

-0.14

aset

-0.14

ÅĻÃŃt

-0.14

enga

-0.13

uti

-0.13

etration

-0.13

FG

-0.13

FM

-0.13

metric

-0.13

POSITIVE LOGITS

oreach

0.15

_CSS

0.15

ahun

0.13

.scalablytyped

0.13

ÑĥÑĢÐ½

0.13

PO

0.13

solete

0.13

 åĨĨ

0.13

 ØªÙĪÙħ

0.13

Activations Density 0.256%

names of people and associated information

No Comments

No Known Activations