INDEX

Explanations

phrases emphasizing quantities or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

icture

-0.17

-0.15

clipse

-0.14

IEW

-0.14

itz

-0.14

bet

-0.14

-caret

-0.14

BackStack

-0.14

uchen

-0.14

ingo

-0.13

POSITIVE LOGITS

 whom

0.15

ovi

0.15

PMC

0.14

LOCKS

0.14

poons

0.14

Ø³Ø§ÙĨÛĮ

0.14

readcr

0.14

ãĥ¬ãĥ¼

0.13

fab

0.13

ras

0.13

Activations Density 0.011%

phrases emphasizing quantities or classifications

No Comments

No Known Activations