INDEX

Explanations

references to educational programs and activities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ocus

-0.16

ìļ±

-0.15

Lorem

-0.15

inta

-0.14

odore

-0.14

banks

-0.14

ugs

-0.14

REATE

-0.13

inee

-0.13

TECTED

-0.13

POSITIVE LOGITS

 Moff

0.17

quivos

0.16

utely

0.16

Eid

0.15

Î¹Î²

0.14

ibold

0.14

gorit

0.14

hole

0.14

igos

0.14

 thous

0.13

Activations Density 1.110%

references to educational programs and activities

No Comments

No Known Activations