INDEX

Explanations

references to events and significant milestones in time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 respective

-0.15

lobe

-0.15

vet

-0.15

roup

-0.15

onse

-0.14

reon

-0.14

inh

-0.14

ording

-0.14

ingen

-0.14

éĮ

-0.14

POSITIVE LOGITS

ê¼

0.15

Â£Â£

0.15

enen

0.14

endir

0.14

ENU

0.13

ardi

0.13

Ub

0.13

chor

0.13

lius

0.13

 belie

0.13

Activations Density 0.134%

references to events and significant milestones in time

No Comments

No Known Activations