INDEX

Explanations

dates and chronological references 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

-0.21

Û²Û°Û±

-0.17

ä¸ĺ

-0.15

 recently

-0.15

edback

-0.15

ufe

-0.15

 recent

-0.14

.va

-0.14

Yesterday

-0.14

:http

-0.14

POSITIVE LOGITS

vard

0.15

beg

0.15

0.14

kin

0.14

NDAR

0.14

or

0.14

Activations Density 0.068%

dates and chronological references in the text

No Comments

No Known Activations

dates and chronological references in the text

No Comments

No Known Activations