INDEX

Explanations

phrases emphasizing conditions, comparisons, and alternatives

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

endon

-0.17

aÄŁa

-0.15

ìłĲ

-0.14

 Cary

-0.14

.ld

-0.14

zon

-0.14

 handler

-0.14

emm

-0.14

emann

-0.14

ure

-0.13

POSITIVE LOGITS

slu

0.15

 circ

0.15

sca

0.15

stalk

0.14

éļ

0.13

ayan

0.13

jen

0.13

Activations Density 0.283%

phrases emphasizing conditions, comparisons, and alternatives

No Comments

No Known Activations

phrases emphasizing conditions, comparisons, and alternatives

No Comments

No Known Activations