INDEX

Explanations

references to the television series "Doctor Who."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

andler

-0.18

@js

-0.18

.Override

-0.14

ÑĩÐµ

-0.14

baum

-0.14

 stack

-0.14

 standardized

-0.13

/stdc

-0.13

åĬŁ

-0.13

POSITIVE LOGITS

 Pert

0.26

 UNIT

0.25

 Dale

0.25

 companions

0.21

UNIT

0.21

 Doctor

0.21

DWC

0.21

 regeneration

0.19

Kro

0.19

 Faction

0.19

Activations Density 0.009%

references to the television series "Doctor Who."

No Comments

No Known Activations