INDEX

Explanations

entities and characters associated with specific events or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

istrat

-0.16

enty

-0.16

apore

-0.15

incr

-0.15

onne

-0.14

 shrink

-0.14

ivas

-0.14

 stat

-0.14

ircraft

-0.14

ply

-0.14

POSITIVE LOGITS

Cro

0.21

Cro

0.21

Gro

0.20

cro

0.19

Gro

0.18

bro

0.18

gro

0.18

BRO

0.18

gro

0.18

Bro

0.17

Activations Density 0.050%

entities and characters associated with specific events or situations

No Comments

No Known Activations