INDEX

Explanations

references to the concept of the past

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Insensitive

-0.17

entai

-0.16

eteria

-0.15

 Sink

-0.14

chair

-0.14

aggable

-0.14

ÑĤÐµÑĢÐ¸

-0.14

ahead

-0.13

eking

-0.13

 chin

-0.13

POSITIVE LOGITS

/current

0.20

ime

0.17

/new

0.17

IME

0.15

yme

0.15

iche

0.14

imes

0.14

/back

0.14

orate

0.14

ERTICAL

0.14

Activations Density 0.063%

references to the concept of the past

No Comments

No Known Activations