INDEX

Explanations

phrases or conjunctions that connect ideas or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 strictly

-0.14

udit

-0.13

 Strict

-0.13

pling

-0.13

cape

-0.13

á»¯

-0.13

Strict

-0.13

aqu

-0.13

_attempts

-0.12

OR

-0.12

POSITIVE LOGITS

raquo

0.17

/or

0.17

ROID

0.16

upil

0.16

Ach

0.14

specs

0.14

/of

0.14

arrant

0.14

argout

0.14

 Wander

0.14

Activations Density 0.055%

phrases or conjunctions that connect ideas or information

No Comments

No Known Activations