INDEX

Explanations

programming-related actions and commands related to data manipulation and event handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

avia

-0.16

adÄ±r

-0.15

appa

-0.14

/******/

-0.14

ods

-0.14

 norge

-0.14

å¢

-0.14

ï»¿#

-0.14

river

-0.13

OLEAN

-0.13

POSITIVE LOGITS

igar

0.15

omba

0.14

NewLabel

0.14

ãĥĥãĥĪ

0.14

semble

0.14

rif

0.14

mlin

0.13

 ÎķÎ½

0.13

caffe

0.13

tie

0.13

Activations Density 0.108%

programming-related actions and commands related to data manipulation and event handling

No Comments

No Known Activations