INDEX

Explanations

specific historical time periods and associated numerical references

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

owers

-0.15

 Laud

-0.14

andom

-0.14

Wyn

-0.14

 radiation

-0.14

æĢĿãģĦ

-0.14

immel

-0.14

iber

-0.14

ama

-0.14

POSITIVE LOGITS

anners

0.15

strand

0.15

odel

0.15

ATEST

0.14

rance

0.14

ranÃŃ

0.14

antz

0.14

ussen

0.14

_TestCase

0.14

ABL

0.14

Activations Density 0.113%

specific historical time periods and associated numerical references

No Comments

No Known Activations