INDEX

Explanations

references to specific historical events and their associated data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

dum

-0.15

dun

-0.14

resenter

-0.14

undry

-0.14

 undesirable

-0.14

dil

-0.14

quence

-0.13

 receivers

-0.13

 extrapol

-0.13

mrt

-0.13

POSITIVE LOGITS

weg

0.15

atz

0.15

OMP

0.14

æĢ

0.14

ogh

0.14

wear

0.14

org

0.13

 ë§ĲìĿ´

0.13

ught

0.13

 phenomen

0.13

Activations Density 0.072%

references to specific historical events and their associated data

No Comments

No Known Activations