INDEX

Explanations

references to brain imaging studies and their implications for psychological conditions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

undra

-0.17

uarios

-0.16

affles

-0.16

ropolis

-0.15

ç®±

-0.15

/cgi

-0.14

igure

-0.14

çĤī

-0.14

apeake

-0.14

OPSIS

-0.14

POSITIVE LOGITS

0.17

apat

0.17

imm

0.16

acker

0.16

ito

0.15

inton

0.15

Ø±Ø§Ùĩ

0.15

orc

0.15

crit

0.14

gend

0.14

Activations Density 0.080%

references to brain imaging studies and their implications for psychological conditions

No Comments

No Known Activations