INDEX

Explanations

punctuation marks, particularly those associated with emotional or expressive conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Sawyer

-0.15

STRACT

-0.14

anh

-0.14

clin

-0.14

ardi

-0.13

ost

-0.13

Ð»Ð°ÑĤÐ¸

-0.13

 Barn

-0.13

asics

-0.13

____________

-0.13

POSITIVE LOGITS

qw

0.15

ophe

0.15

Ð¾ÑĤÑĭ

0.14

orus

0.14

·»

0.14

lÃŃ

0.14

 domest

0.14

_levels

0.14

 levels

0.14

yw

0.13

Activations Density 0.082%

punctuation marks, particularly those associated with emotional or expressive conclusions

No Comments

No Known Activations