INDEX

Explanations

references to years and significant events or milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

cth

-0.16

BindingUtil

-0.16

enou

-0.15

imedia

-0.15

ocity

-0.15

OrCreate

-0.14

uji

-0.14

untime

-0.14

NTAX

-0.14

nda

-0.14

POSITIVE LOGITS

 Alta

0.14

ponder

0.13

 contrary

0.13

otal

0.13

ÑĥÐ·

0.13

 organis

0.13

 å¡

0.13

.met

0.13

Sil

0.13

Activations Density 0.121%

references to years and significant events or milestones

No Comments

No Known Activations