INDEX

Explanations

mentions of guests

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

istan

-0.17

osg

-0.16

ancock

-0.16

erus

-0.16

ham

-0.15

illas

-0.15

indered

-0.15

ÑĢÐ¾Ð¶

-0.15

erb

-0.14

zm

-0.14

POSITIVE LOGITS

richt

0.15

 boot

0.15

kla

0.14

æĮģãģ¡

0.14

æĤł

0.14

neau

0.14

afari

0.14

urname

0.13

 Conte

0.13

acters

0.13

Activations Density 0.008%

mentions of guests

No Comments

No Known Activations