INDEX

Explanations

references to systems or mechanisms identified as "apparatus."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

emax

-0.17

fsp

-0.15

bracht

-0.15

versation

-0.15

ĨĴ

-0.15

.scalajs

-0.14

jections

-0.14

mont

-0.14

.innerHeight

-0.14

lal

-0.14

POSITIVE LOGITS

0.17

0.16

ulin

0.16

 tard

0.16

ilt

0.15

 Andrews

0.15

ãģį

0.15

one

0.14

ki

0.14

Activations Density 0.010%

references to systems or mechanisms identified as "apparatus."

No Comments

No Known Activations