INDEX

Explanations

specific species names and their classifications in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ddl

-0.15

cci

-0.14

hani

-0.14

acific

-0.14

æŀ

-0.14

illary

-0.14

.openConnection

-0.14

Î´Î®

-0.13

_REF

-0.13

vero

-0.13

POSITIVE LOGITS

 Marion

0.16

ally

0.15

ANS

0.15

ALSE

0.15

ales

0.14

Paste

0.14

 Paste

0.14

esser

0.14

unks

0.14

otes

0.14

Activations Density 0.063%

specific species names and their classifications in a scientific context

No Comments

No Known Activations