INDEX

Explanations

technical terminology related to programming languages and their specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Clyde

-0.14

 Dillon

-0.14

chn

-0.14

ãĥ«ãĤ¯

-0.14

ohl

-0.14

thane

-0.14

 trace

-0.14

ehir

-0.14

dataTable

-0.14

 PureComponent

-0.14

POSITIVE LOGITS

0.16

 sice

0.15

idas

0.15

iÃ¨res

0.15

 automÃ¡t

0.14

led

0.14

MBER

0.14

nings

0.14

INET

0.14

ensis

0.14

Activations Density 0.002%

technical terminology related to programming languages and their specifications

No Comments

No Known Activations