INDEX

Explanations

phrases expressing doubt and uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

utor

-0.17

rif

-0.17

edla

-0.16

INTR

-0.15

tir

-0.15

tuk

-0.15

hong

-0.15

 darm

-0.14

_CLIP

-0.14

ivor

-0.14

POSITIVE LOGITS

 somewhere

0.22

 somehow

0.18

 similarly

0.17

 since

0.16

 alguna

0.16

 irgend

0.15

 algÃºn

0.15

 somew

0.15

 considering

0.14

ason

0.14

Activations Density 0.271%

phrases expressing doubt and uncertainty

No Comments

No Known Activations