INDEX

Explanations

terms and concepts related to mediation and mediators

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

ThanOr

-0.17

ibli

-0.15

/autoload

-0.15

neau

-0.15

__':↵

-0.14

 Shoulder

-0.14

sd

-0.14

 addCriterion

-0.14

utral

-0.14

esin

-0.14

POSITIVE LOGITS

lessly

0.15

elt

0.15

atively

0.14

 Blitz

0.14

_ext

0.14

rief

0.14

erno

0.14

ely

0.14

oppel

0.13

 instruct

0.13

Activations Density 0.012%

terms and concepts related to mediation and mediators

No Comments

No Known Activations