INDEX

Explanations

elements related to significant events or pivotal moments in a storyline

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

//{{

-0.15

udded

-0.15

 Gust

-0.15

ete

-0.14

igm

-0.14

Kra

-0.14

 Procedure

-0.14

sme

-0.14

proc

-0.14

ounty

-0.13

POSITIVE LOGITS

 Wheel

0.20

ayne

0.18

Wheel

0.18

 Demand

0.16

_wheel

0.16

zbek

0.16

Tar

0.15

verity

0.15

 Rand

0.15

íĨµ

0.15

Activations Density 0.007%

elements related to significant events or pivotal moments in a storyline

No Comments

No Known Activations