INDEX

Explanations

technical jargon and specific terms related to engineering or technology

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

uft

-0.16

ICS

-0.16

ics

-0.16

Ã©ment

-0.15

uko

-0.14

ãĥ«ãĥī

-0.14

rello

-0.14

eÄį

-0.14

 Ders

-0.14

å´

-0.14

POSITIVE LOGITS

gel

0.16

 Mellon

0.15

ndern

0.15

coli

0.14

nerg

0.14

CALE

0.14

Gel

0.14

 benchmark

0.13

 Bowl

0.13

indow

0.13

Activations Density 0.010%

technical jargon and specific terms related to engineering or technology

No Comments

No Known Activations