INDEX

Explanations

occurrences of the keyword "def" which typically indicates the definition of functions in programming

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oge

-0.17

spam

-0.15

vfs

-0.15

RAND

-0.15

acco

-0.15

TimeZone

-0.15

afil

-0.14

ofire

-0.14

pane

-0.14

 seedu

-0.14

POSITIVE LOGITS

Disposed

0.16

aye

0.15

Ree

0.15

keh

0.14

inv

0.14

EN

0.14

auce

0.14

gra

0.14

Rex

0.13

Ard

0.13

Activations Density 0.002%

occurrences of the keyword "def" which typically indicates the definition of functions in programming

No Comments

No Known Activations