INDEX

Explanations

occurrences of the term "involving."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ska

-0.17

vale

-0.15

ichel

-0.15

ahlen

-0.15

ahren

-0.14

ilden

-0.14

odel

-0.14

Å¡ka

-0.14

iento

-0.13

endencies

-0.13

POSITIVE LOGITS

0.14

uci

0.14

ELS

0.14

arel

0.14

anian

0.14

PAD

0.14

 Exped

0.13

ReadStream

0.13

stand

0.13

Activations Density 0.005%

occurrences of the term "involving."

No Comments

No Known Activations