INDEX

Explanations

numeric values and relevant dates or periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

-0.19

cup

-0.16

issen

-0.16

 source

-0.15

cup

-0.15

↵

-0.15

lex

-0.15

 Helen

-0.15

zing

-0.15

arta

-0.15

POSITIVE LOGITS

-LAST

0.18

indre

0.17

OffsetTable

0.16

QRST

0.16

PLIT

0.16

 lÃ´

0.15

ocale

0.15

 canh

0.15

ULA

0.15

Î¹Ïİ

0.15

Activations Density 0.005%

numeric values and relevant dates or periods

No Comments

No Known Activations