INDEX

Explanations

objects and concepts associated with space and utility

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

usch

-0.16

.cond

-0.15

/dat

-0.15

 Burgess

-0.15

ime

-0.15

ãĥ¼ãĥŃ

-0.15

arden

-0.15

orgot

-0.14

 Resolver

-0.14

POSITIVE LOGITS

AspectRatio

0.17

[]=$

0.16

etically

0.15

ityEngine

0.15

ï»¿#

0.15

.fromFunction

0.15

ombo

0.15

ksam

0.15

ãģ¨ãģĹãģ¦

0.14

afx

0.14

Activations Density 0.146%

objects and concepts associated with space and utility

No Comments

No Known Activations