INDEX

Explanations

words related to scientific research or classification, particularly focusing on specific plants and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

heim

-0.15

Ø´ÙħØ§ÙĦÛĮ

-0.15

aret

-0.15

ãĥ©ãĥ¼

-0.15

achts

-0.15

ãĥĭãĥ¼

-0.14

ens

-0.14

brero

-0.14

taj

-0.14

lotte

-0.14

POSITIVE LOGITS

Tek

0.15

jmp

0.15

ewan

0.14

 Shank

0.14

ukan

0.14

 contrary

0.14

stamp

0.14

 nutshell

0.13

agne

0.13

plx

0.13

Activations Density 0.060%

words related to scientific research or classification, particularly focusing on specific plants and their properties

No Comments

No Known Activations