INDEX

Explanations

references to specific locations and details related to reported incidents or events

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aphrag

-0.16

retty

-0.15

 ragaz

-0.15

orro

-0.14

PLICIT

-0.14

ansion

-0.14

AU

-0.14

ansas

-0.14

datable

-0.14

iid

-0.14

POSITIVE LOGITS

ycz

0.17

Fi

0.16

Ð²Ð°Ð¶

0.14

yna

0.14

nob

0.14

hop

0.14

ASCADE

0.14

ym

0.14

 CLEAR

0.14

Sphere

0.13

Activations Density 0.334%

references to specific locations and details related to reported incidents or events

No Comments

No Known Activations