INDEX

Explanations

actions and responses in the context of communication and management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

lify

-0.17

acker

-0.17

scribe

-0.16

owing

-0.16

EMU

-0.15

gren

-0.15

ordin

-0.15

-urlencoded

-0.15

Ø¬Ø§Ø¯

-0.15

POSITIVE LOGITS

ments

0.27

ance

0.26

ings

0.25

able

0.24

ances

0.24

ability

0.24

ables

0.22

ative

0.20

ants

0.20

ations

0.19

Activations Density 0.267%

actions and responses in the context of communication and management

No Comments

No Known Activations