INDEX

Explanations

references to different modes or forms of gameplay

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ocht

-0.14

EFR

-0.14

ensive

-0.14

ves

-0.14

=forms

-0.14

 knull

-0.14

ISC

-0.14

iste

-0.13

uum

-0.13

Jug

-0.13

POSITIVE LOGITS

tere

0.15

zac

0.14

.nz

0.14

 ticking

0.14

 reordered

0.14

/down

0.14

ill

0.14

iller

0.13

-down

0.13

-as

0.13

Activations Density 0.010%

references to different modes or forms of gameplay

No Comments

No Known Activations

references to different modes or forms of gameplay

No Comments

No Known Activations