INDEX

Explanations

comparisons between human capabilities and machine processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

overe

-0.16

ahun

-0.14

Î²Î¬

-0.14

isode

-0.14

_OW

-0.14

.threshold

-0.14

loff

-0.14

ativas

-0.14

 GtkWidget

-0.13

.getMethod

-0.13

POSITIVE LOGITS

anel

0.17

enko

0.16

ampo

0.15

_CAPACITY

0.14

 Hind

0.14

hind

0.14

 capacity

0.14

 gang

0.13

 Niagara

0.13

 Widow

0.13

Activations Density 0.183%

comparisons between human capabilities and machine processes

No Comments

No Known Activations