INDEX

Explanations

alphanumeric characters and symbols typically seen in data or coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

abbo

-0.22

 Sachs

-0.18

sch

-0.15

Æ°á»¡ng

-0.15

 EntryPoint

-0.15

aland

-0.15

dq

-0.15

etro

-0.14

viron

-0.14

visor

-0.14

POSITIVE LOGITS

uan

0.24

0.19

uc

0.18

ÙĪØ§ÙĨ

0.18

ua

0.18

 Cougar

0.16

ody

0.15

ocy

0.14

sey

0.14

Activations Density 0.001%

alphanumeric characters and symbols typically seen in data or coding contexts

No Comments

No Known Activations