INDEX

Explanations

sections of code or text that denote the end of a block or function

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

isko

-0.15

legg

-0.15

gett

-0.15

inst

-0.14

asset

-0.14

lisi

-0.14

ammad

-0.14

unte

-0.14

stra

-0.14

.escape

-0.13

POSITIVE LOGITS

 Glas

0.18

.GetText

0.15

ervals

0.15

olist

0.14

vrier

0.14

 Ð³Ð»Ñĥ

0.14

pecified

0.14

abei

0.14

IfNeeded

0.13

iyon

0.13

Activations Density 0.000%

sections of code or text that denote the end of a block or function

No Comments

No Known Activations