INDEX

Explanations

recurring references to setup instructions or processes in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

net

-0.17

part

-0.15

ound

-0.15

pool

-0.15

gate

-0.15

ongan

-0.15

oure

-0.14

nap

-0.14

sted

-0.14

ato

-0.14

POSITIVE LOGITS

urovision

0.17

vem

0.16

 FontWeight

0.16

Îŀ

0.16

ÙĬØ©

0.15

icontrol

0.15

afx

0.15

otland

0.15

MOTE

0.15

irit

0.15

Activations Density 0.011%

recurring references to setup instructions or processes in a technical context

No Comments

No Known Activations