INDEX

Explanations

technical or programming-related terms and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

_intr

-0.14

uchar

-0.14

.MixedReality

-0.14

 ÙħØªØ±

-0.13

Ngb

-0.13

.tv

-0.13

.DataBind

-0.13

Ø±Ø²

-0.13

_lift

-0.13

idot

-0.13

POSITIVE LOGITS

Ali

0.22

 calor

0.20

 ROOT

0.20

 charged

0.20

 shower

0.19

 cuts

0.19

Ali

0.19

 veto

0.19

 showers

0.19

 Shower

0.18

Activations Density 0.001%

technical or programming-related terms and symbols

No Comments

No Known Activations