INDEX

Explanations

references to specific countries or territories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

OMPI

-0.15

angl

-0.15

_PACK

-0.15

preneur

-0.15

ugu

-0.15

ibi

-0.14

opsis

-0.14

Ø§ÙĨÙĩ

-0.14

orte

-0.14

POSITIVE LOGITS

 âĢİ

0.14

(UI

0.14

bose

0.14

modulo

0.14

ê°Ħ

0.14

 Hale

0.13

âĢİ

0.13

apat

0.13

nt

0.13

kÃ½

0.13

Activations Density 0.061%

references to specific countries or territories

No Comments

No Known Activations