INDEX

Explanations

references to specific years or dates in literary contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

inee

-0.18

ilos

-0.15

tw

-0.14

iffin

-0.14

ibble

-0.14

fone

-0.14

Pix

-0.13

ãĤ¦ãĤ¹

-0.13

 clipped

-0.13

 Clips

-0.13

POSITIVE LOGITS

ropy

0.17

ambre

0.15

Delimiter

0.15

ering

0.14

ichert

0.14

iche

0.14

ãĥªãĥ³ãĤ°

0.14

phere

0.14

 Desc

0.14

Activations Density 0.027%

references to specific years or dates in literary contexts

No Comments

No Known Activations