INDEX

Explanations

occurrences of emotional expressions and interpersonal interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

infer

-0.17

worthy

-0.16

iffer

-0.16

elles

-0.15

avel

-0.15

ovel

-0.15

andon

-0.14

ellers

-0.14

uls

-0.13

atty

-0.13

POSITIVE LOGITS

ç»ĵæŀľ

0.19

 result

0.19

çµĲæŀľ

0.19

 resulted

0.18

 Result

0.17

ãĤ«ãĥ¼

0.17

 results

0.17

 Ergebn

0.16

 resulting

0.16

 Results

0.16

Activations Density 0.273%

occurrences of emotional expressions and interpersonal interactions

No Comments

No Known Activations