INDEX

Explanations

phrases indicating uncertainty and causation in complex situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

oley

-0.16

quan

-0.15

zin

-0.15

ulu

-0.15

eward

-0.15

 Yeah

-0.15

ymph

-0.14

 yeah

-0.14

ammers

-0.14

POSITIVE LOGITS

 Nature

0.19

Nature

0.17

such

0.17

soever

0.16

itis

0.15

 such

0.15

vyh

0.14

 nature

0.14

 Such

0.14

 there

0.14

Activations Density 0.440%

phrases indicating uncertainty and causation in complex situations

No Comments

No Known Activations