INDEX

Explanations

references to military forces and conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

rosso

-0.20

anou

-0.16

quam

-0.15

eyim

-0.15

ascade

-0.15

yon

-0.14

USH

-0.14

rium

-0.14

laden

-0.14

iben

-0.14

POSITIVE LOGITS

å£

0.17

 strength

0.14

 equivalence

0.14

ox

0.14

SA

0.14

 whistleblower

0.14

0.13

Bed

0.13

itech

0.13

 Rent

0.13

Activations Density 0.115%

references to military forces and conflicts

No Comments

No Known Activations