INDEX

Explanations

expressions of positive emotions and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

pig

-0.14

UIAlertAction

-0.14

ibraries

-0.14

arden

-0.14

Pig

-0.14

obraz

-0.14

.TODO

-0.14

.randomUUID

-0.13

oggler

-0.13

 diff

-0.13

POSITIVE LOGITS

bon

0.16

tha

0.15

inge

0.15

abi

0.15

abel

0.14

 sink

0.14

Lah

0.14

ãĥªãĥ¼ãĤº

0.14

lah

0.14

etto

0.13

Activations Density 0.362%

expressions of positive emotions and experiences

No Comments

No Known Activations