INDEX

Explanations

words and terms associated with critical assessments or evaluations

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

eties

-0.17

utm

-0.15

eteria

-0.15

anza

-0.14

ilio

-0.14

æ¦ľ

-0.14

elia

-0.14

adesh

-0.14

.Ptr

-0.14

okud

-0.14

POSITIVE LOGITS

 Eden

0.17

ed

0.15

idge

0.15

Lat

0.14

ogi

0.14

afen

0.14

ahlen

0.14

ÑĢÐ°Ð²Ð¸

0.13

Lat

0.13

borg

0.13

Activations Density 0.014%

words and terms associated with critical assessments or evaluations

No Comments

No Known Activations