INDEX

Explanations

numeric values and dates

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ï»¿↵↵

-0.16

æĹıèĩªæ²»

-0.15

oth

-0.15

avanaugh

-0.15

-0.14

 reve

-0.14

ÌĤ

-0.14

 Trap

-0.14

Ð½ÑĮ

-0.14

net

-0.14

POSITIVE LOGITS

_simps

0.16

mess

0.16

imet

0.15

ahy

0.15

ungle

0.15

addir

0.15

coh

0.14

mes

0.14

trag

0.14

licit

0.14

Activations Density 0.003%

numeric values and dates

No Comments

No Known Activations