INDEX

Explanations

expressions of self-doubt and uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

indle

-0.16

ãģªãĤĵãģ¦

-0.15

 äºļæ´²

-0.14

ãģªãģ®

-0.14

ãģĵãĤĵãģ«ãģ¡ãģ¯

-0.14

warts

-0.14

ãģŁãģ¡ãģ¯

-0.14

ãģĤãĤĬãģĮãģ¨ãģĨ

-0.13

 Quantum

-0.13

 nearly

-0.13

POSITIVE LOGITS

.vaadin

0.15

 çĬ

0.15

 giÃ³

0.14

ĢìĿ´

0.14

 Ð±ÑĥÐ´ÑĤÐ¾

0.14

mlx

0.13

ãĥ¼ãĥĢ

0.13

emes

0.13

Ð°ÑĢÐ°Ð¼

0.13

 Cunning

0.13

Activations Density 0.006%

expressions of self-doubt and uncertainty

No Comments

No Known Activations