INDEX

Explanations

references to tactical situations and cover in a combat context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ohana

-0.18

 åĨĨ

-0.18

 Archives

-0.15

udies

-0.15

ehir

-0.15

 captive

-0.15

cest

-0.14

 ÙĨØ³Ø¨

-0.14

.sul

-0.14

reon

-0.14

POSITIVE LOGITS

_utilities

0.17

 conceal

0.16

èĹı

0.15

 hiding

0.15

 ìĪ¨

0.15

_HIDE

0.15

 cover

0.15

 shadows

0.15

Å¸

0.15

 hide

0.15

Activations Density 0.176%

references to tactical situations and cover in a combat context

No Comments

No Known Activations