INDEX

Explanations

terms related to drugs and drug-related concepts

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

agnar

-0.17

eners

-0.16

ipsis

-0.16

est

-0.15

anness

-0.15

ãĥ£

-0.15

ogl

-0.14

iyas

-0.14

ooth

-0.14

 Patri

-0.14

POSITIVE LOGITS

store

0.29

stores

0.24

STORE

0.20

OD

0.17

 lords

0.17

ger

0.17

/device

0.17

-device

0.16

 Enforcement

0.16

 lord

0.16

Activations Density 0.020%

terms related to drugs and drug-related concepts

No Comments

No Known Activations