INDEX

Explanations

numeric values or codes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Äĥn

-0.16

isci

-0.15

iana

-0.15

pl

-0.14

pl

-0.14

uss

-0.14

etch

-0.14

onne

-0.14

ann

-0.14

 Hann

-0.14

POSITIVE LOGITS

kyt

0.16

iliz

0.15

ìĶ¨

0.15

Forgery

0.14

è¦

0.14

tain

0.14

Î³Îµ

0.14

utom

0.14

Ngh

0.14

"\↵

0.14

Activations Density 0.002%

numeric values or codes

No Comments

No Known Activations