INDEX

Explanations

non-English characters or symbols in the text

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

¶ģ

-0.16

¦¬

-0.15

viron

-0.15

áº¿u

-0.15

-0.14

/fw

-0.14

aset

-0.13

obook

-0.13

¯¼

-0.13

 Rich

-0.13

POSITIVE LOGITS

Ģ

0.25

Ĵ

0.21

ģ

0.20

Ħ

0.19

ı

0.18

ĥ

0.17

Ĳ

0.17

İ

0.16

ĵ

0.16

Ŀ

0.16

Activations Density 0.011%

non-English characters or symbols in the text

No Comments

No Known Activations