INDEX

Explanations

phrases related to inquiries or requests for information

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

eri

-0.14

Ã±

-0.14

Ã»t

-0.14

 Ã¡n

-0.14

Begin

-0.14

ansen

-0.14

ichte

-0.14

Ã©g

-0.14

onte

-0.13

etCode

-0.13

POSITIVE LOGITS

TypeID

0.14

than

0.14

swire

0.14

 bÃ²

0.14

noinspection

0.14

ItemId

0.14

casts

0.14

lesh

0.14

 than

0.14

rank

0.14

Activations Density 0.028%

phrases related to inquiries or requests for information

No Comments

No Known Activations