INDEX

Explanations

terms and phrases related to legal or bureaucratic processes involving documentation and compliance

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

anova

-0.16

apia

-0.16

ksam

-0.14

_PROC

-0.14

 notebooks

-0.14

isse

-0.13

aggio

-0.13

ivate

-0.13

Ãµi

-0.13

POSITIVE LOGITS

 Shades

0.14

roller

0.14

endar

0.14

 èı²

0.14

Å¯st

0.14

.slim

0.13

iÄĻ

0.13

chang

0.13

zon

0.13

olumn

0.13

Activations Density 0.020%

terms and phrases related to legal or bureaucratic processes involving documentation and compliance

No Comments

No Known Activations