INDEX

Explanations

terms related to organizations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ubits

-0.17

izen

-0.17

izens

-0.16

 Bias

-0.15

ohana

-0.15

emp

-0.14

çĸĨ

-0.14

aub

-0.14

Ø±Ùĩ

-0.14

µ

-0.14

POSITIVE LOGITS

Ri

0.17

iles

0.15

kea

0.15

Ø§Ø´Øª

0.14

ries

0.14

 VÅ¡

0.14

CastException

0.13

ekler

0.13

èī

0.13

eba

0.13

Activations Density 0.073%

terms related to organizations and institutions

No Comments

No Known Activations