INDEX

Explanations

numerical identifiers and values in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Poss

-0.17

Ã¸d

-0.14

ÐµÐ²Ð¸Ð´

-0.14

jah

-0.14

MAN

-0.14

 possibilities

-0.14

Gow

-0.14

zu

-0.13

 jury

-0.13

 laisse

-0.13

POSITIVE LOGITS

ãĥ³ãĤ¬

0.16

itele

0.16

elle

0.16

iteli

0.15

utzer

0.14

pathname

0.14

appendTo

0.14

ysz

0.14

/XMLSchema

0.14

.getDefault

0.14

Activations Density 0.088%

numerical identifiers and values in context

No Comments

No Known Activations