INDEX

Explanations

identifiers related to legal case citations and patent references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

lsen

-0.19

otation

-0.14

uels

-0.14

 Atkins

-0.14

Ð°ÑĤÐ¾ÑĢ

-0.14

oles

-0.14

eel

-0.13

ead

-0.13

ivate

-0.13

enser

-0.13

POSITIVE LOGITS

 èĪ

0.15

{{{

0.15

 Splash

0.15

iÅ¡

0.14

Splash

0.14

 seedu

0.14

Conference

0.14

hum

0.14

tar

0.14

Activations Density 0.010%

identifiers related to legal case citations and patent references

No Comments

No Known Activations