INDEX

Explanations

references to geographical locations or points of interest

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

æĭĶ

-0.16

udden

-0.16

odings

-0.15

stellen

-0.15

riere

-0.15

olarity

-0.15

ropy

-0.15

æŁ±

-0.14

Mi

-0.14

vero

-0.14

POSITIVE LOGITS

 Tough

0.16

obi

0.16

ing

0.15

 Tune

0.14

LOCKS

0.14

rott

0.14

esimal

0.14

tron

0.13

 dereg

0.13

 Trap

0.13

Activations Density 0.006%

references to geographical locations or points of interest

No Comments

No Known Activations