INDEX

Explanations

directional indicators and location references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

alim

-0.19

Dud

-0.19

oise

-0.17

/interfaces

-0.16

.tc

-0.15

ucu

-0.15

ucer

-0.15

lord

-0.15

Ø´Ø§ÙĨ

-0.15

cott

-0.15

POSITIVE LOGITS

 left

0.15

MLS

0.14

Î»Î¬

0.14

FD

0.14

prak

0.14

Poz

0.13

ç¨¿

0.13

brief

0.13

left

0.13

Activations Density 0.032%

directional indicators and location references

No Comments

No Known Activations

directional indicators and location references

No Comments

No Known Activations