INDEX

Explanations

the word "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

occo

-0.16

opp

-0.15

agar

-0.14

.execution

-0.14

weather

-0.14

agle

-0.14

ething

-0.14

hoff

-0.13

Ø³Ø§ÙĨ

-0.13

Î¯Ïĥ

-0.13

POSITIVE LOGITS

jab

0.16

lac

0.14

 Anatomy

0.14

reff

0.14

visor

0.14

 inert

0.13

qrt

0.13

ãĥ³ãĥĸ

0.13

LEAR

0.13

 Governance

0.12

Activations Density 0.343%

the word "that" in various contexts

No Comments

No Known Activations