INDEX

Explanations

references to "Lie" and related phrases or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 addCriterion

-0.17

_INITIALIZER

-0.16

adesh

-0.15

unist

-0.14

WARDED

-0.14

Ø§ÙħÛĮÙĨ

-0.14

nist

-0.14

.ManyToMany

-0.14

_EXECUTE

-0.14

aversable

-0.14

POSITIVE LOGITS

ffect

0.15

 intensity

0.15

atform

0.15

at

0.15

ofilm

0.14

 escal

0.14

à¤®à¤ķ

0.14

Lab

0.14

enge

0.14

ileged

0.14

Activations Density 0.017%

references to "Lie" and related phrases or concepts

No Comments

No Known Activations