INDEX

Explanations

references to specific universities, especially those in California and Texas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ãĥ«ãĥī

-0.17

cona

-0.15

qus

-0.15

PARATOR

-0.15

ureau

-0.15

¢åįķ

-0.14

 scissors

-0.14

 Accum

-0.14

.getOwnProperty

-0.13

LAP

-0.13

POSITIVE LOGITS

0.17

upo

0.15

ahoo

0.15

 plates

0.14

 Jacobs

0.14

oen

0.13

rons

0.13

TM

0.13

Activations Density 0.040%

references to specific universities, especially those in California and Texas

No Comments

No Known Activations