INDEX

Explanations

terms related to discovery and findings

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

sian

-0.16

æĮģ

-0.14

inx

-0.14

outers

-0.14

outer

-0.14

SED

-0.13

 prominent

-0.13

itan

-0.13

 Beaver

-0.13

ãĤ

-0.13

POSITIVE LOGITS

.opens

0.15

agma

0.15

aldi

0.15

alls

0.15

 ----------------------------------------------------------------------------↵

0.15

 ---------------------------------------------------------------------------↵

0.15

ãĥĬãĥ«

0.14

ãĥ³ãĤº

0.14

cope

0.13

Norm

0.13

Activations Density 0.008%

terms related to discovery and findings

No Comments

No Known Activations