INDEX

Explanations

phrases related to "value-added" concepts in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

rott

-0.17

 çĨ

-0.15

 spat

-0.14

wo

-0.14

([],

-0.14

vou

-0.14

 rencontr

-0.13

iov

-0.13

uelles

-0.13

indle

-0.13

POSITIVE LOGITS

abyte

0.16

cts

0.15

Ã©sz

0.14

 pole

0.14

ÙĨØ§

0.14

ìĦĿ

0.14

feb

0.14

PLETED

0.14

ansson

0.13

Activations Density 0.012%

phrases related to "value-added" concepts in various contexts

No Comments

No Known Activations