INDEX

Explanations

phrases or constructions related to the concept of "up."

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

sing

-0.17

tet

-0.17

cko

-0.16

ERO

-0.15

tip

-0.15

 bend

-0.14

entials

-0.14

ÙģÙĩ

-0.14

llx

-0.14

erca

-0.13

POSITIVE LOGITS

usta

0.16

0.15

OSC

0.15

ãĤ¯

0.14

normalize

0.14

abra

0.14

emsp

0.14

 {?>↵

0.13

emi

0.13

jax

0.13

Activations Density 0.010%

phrases or constructions related to the concept of "up."

No Comments

No Known Activations