INDEX

Explanations

numerical representations of biblical or historical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

oshi

-0.15

 legit

-0.15

ometric

-0.14

èĬĻ

-0.14

iggins

-0.14

 perg

-0.14

 Briggs

-0.14

pek

-0.14

 Agenda

-0.14

POSITIVE LOGITS

.ContextCompat

0.20

rias

0.17

xit

0.16

ìĿ´íĬ¸

0.16

ollower

0.15

ipelines

0.15

Ã½t

0.14

Ð¾Ð»Ð¾Ñģ

0.14

rier

0.14

ria

0.14

Activations Density 0.053%

numerical representations of biblical or historical references

No Comments

No Known Activations