INDEX

Explanations

words related to categories or classifications

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

 Evidence

-0.15

TBD

-0.14

 evidence

-0.14

 Hats

-0.14

 Platinum

-0.14

Nit

-0.13

ussen

-0.13

ellen

-0.13

py

-0.13

elden

-0.13

POSITIVE LOGITS

/classes

0.16

Ã¶st

0.15

adera

0.15

à¤Ĺà¤²

0.15

ochen

0.14

 thÃ¹

0.14

pron

0.14

ê°Ħ

0.14

aÅ¼

0.13

horn

0.13

Activations Density 0.006%

words related to categories or classifications

No Comments

No Known Activations