INDEX

Explanations

references to educational institutions and related geographic activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

reau

-0.16

hem

-0.16

ynos

-0.15

_rt

-0.15

èĩ

-0.15

laus

-0.14

Ã²i

-0.14

ulace

-0.14

czy

-0.14

hem

-0.14

POSITIVE LOGITS

 Wichita

0.38

 Kansas

0.34

Kansas

0.33

KS

0.25

USD

0.25

0.23

USD

0.23

 Hutchinson

0.22

 wich

0.22

 Dodge

0.22

Activations Density 0.019%

references to educational institutions and related geographic activities

No Comments

No Known Activations