INDEX

Explanations

corporate jargon and terminology related to business or industry contexts

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

addock

-0.23

ckett

-0.15

Sno

-0.15

RESET

-0.15

enos

-0.14

rak

-0.14

Ã´t

-0.14

anna

-0.14

quet

-0.13

leur

-0.13

POSITIVE LOGITS

ru

0.17

rve

0.15

ursor

0.14

iw

0.14

lers

0.13

rz

0.13

 mimic

0.13

esi

0.13

 rivers

0.13

peq

0.13

Activations Density 0.000%

corporate jargon and terminology related to business or industry contexts

No Comments

No Known Activations