INDEX

Explanations

terms related to military force and weaponry

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

enance

-0.17

tle

-0.16

ease

-0.15

ane

-0.15

edy

-0.15

esto

-0.15

Å¡ka

-0.14

ãĥ£

-0.14

eners

-0.14

ÏĢÎŃ

-0.14

POSITIVE LOGITS

mith

0.23

 mastur

0.15

quete

0.15

kel

0.14

.isNull

0.14

nit

0.14

 interchange

0.14

à¸¨à¸²à¸ªà¸ķà¸£

0.14

ament

0.13

Activations Density 0.037%

terms related to military force and weaponry

No Comments

No Known Activations