INDEX

Explanations

phrases related to academic programs, specifically PhD studies and related opportunities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

inar

-0.16

 Schw

-0.15

reh

-0.14

Ear

-0.14

 opposite

-0.14

LAR

-0.13

Asc

-0.13

inker

-0.13

aka

-0.13

ear

-0.13

POSITIVE LOGITS

åŁ¹è®Ń

0.16

aÅŁ

0.16

ìĤ¬ë¬´

0.16

Ä±rak

0.15

 POINTER

0.14

.tail

0.14

veau

0.14

çĭĲ

0.14

 STATUS

0.14

inox

0.14

Activations Density 0.019%

phrases related to academic programs, specifically PhD studies and related opportunities

No Comments

No Known Activations