INDEX

Explanations

phrases and terms related to quantities and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

airs

-0.18

-0.17

uga

-0.15

DIS

-0.15

zo

-0.15

ken

-0.15

gra

-0.14

obar

-0.14

all

-0.14

amburg

-0.14

POSITIVE LOGITS

-thirds

0.19

nd

0.16

gether

0.16

/th

0.16

ispecies

0.15

athers

0.15

ernaut

0.15

inding

0.14

 tandem

0.14

amber

0.14

Activations Density 0.498%

phrases and terms related to quantities and measurements

No Comments

No Known Activations