INDEX

Explanations

numerical values and related formatting in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

kinci

-0.17

@brief

-0.15

iska

-0.15

klÃ¤

-0.14

 Geile

-0.14

acht

-0.14

lik

-0.14

Ãı

-0.14

tob

-0.13

oogle

-0.13

POSITIVE LOGITS

hetto

0.16

ICO

0.16

0.15

Rae

0.15

ï½ľ

0.15

oreach

0.15

.executor

0.14

urat

0.14

(P

0.14

Activations Density 0.013%

numerical values and related formatting in technical contexts

No Comments

No Known Activations