INDEX

Explanations

relationships and familial connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

iens

-0.16

IB

-0.16

itar

-0.16

inic

-0.15

 Masc

-0.15

 Taylor

-0.14

yat

-0.14

gv

-0.14

 saint

-0.14

ritch

-0.13

POSITIVE LOGITS

0.15

ãĥ¬ãĥ¼

0.15

iso

0.14

odef

0.14

 à¤¸à¤¦

0.14

legg

0.14

umen

0.14

çĳŁ

0.14

 Spit

0.14

ë¨¹

0.14

Activations Density 0.373%

relationships and familial connections

No Comments

No Known Activations