INDEX

Explanations

references to ordinal indicators or positions in a sequence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

egin

-0.15

rine

-0.15

Ø¨Ø§

-0.14

 há»¯u

-0.14

 fisse

-0.14

.setter

-0.13

rint

-0.13

eness

-0.13

Ð²Ð¸Ð´

-0.13

amage

-0.13

POSITIVE LOGITS

arily

0.18

reno

0.17

ousand

0.17

/th

0.17

-generation

0.17

ousands

0.17

oley

0.15

icks

0.15

-largest

0.15

ments

0.15

Activations Density 0.042%

references to ordinal indicators or positions in a sequence

No Comments

No Known Activations