INDEX

Explanations

references to governmental or administrative structures and processes

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

New Auto-Interp

Configuration

fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_mlp_out

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

-of

-0.16

elay

-0.16

bsite

-0.16

Ã¦r

-0.15

.bb

-0.15

PIX

-0.15

_gettime

-0.14

jez

-0.14

-with

-0.14

Unsafe

-0.14

POSITIVE LOGITS

ivity

0.16

mess

0.15

wdx

0.15

 Worcester

0.14

dit

0.14

 Isles

0.14

ãĥĪãĥª

0.14

Riv

0.14

lington

0.14

Activations Density 0.615%

references to governmental or administrative structures and processes

No Comments

No Known Activations