INDEX

Explanations

names and terms related to specific geographical locations or cultural references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

emble

-0.17

 extremes

-0.15

/=

-0.14

 Scient

-0.14

illet

-0.14

gn

-0.13

otes

-0.13

 ÑĩÐ¸Ð½

-0.13

zioni

-0.13

uth

-0.13

POSITIVE LOGITS

peare

0.22

igans

0.17

/Sh

0.16

achat

0.16

0.15

à¥ģà¤Ĩà¤¤

0.15

poke

0.15

0.14

ãĥ¬ãĥ¼

0.14

 didSelectRowAtIndexPath

0.14

Activations Density 0.045%

names and terms related to specific geographical locations or cultural references

No Comments

No Known Activations