INDEX

Explanations

terms related to biology, specifically taxonomy and classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

//{{

-0.14

iangle

-0.13

 Darling

-0.13

 Damian

-0.13

ÏįÏĢ

-0.13

 Rubio

-0.12

ãĥ³ãĥĨ

-0.12

enties

-0.12

 lyon

-0.12

POSITIVE LOGITS

od

1.16

OD

1.02

ods

0.90

Hod

0.88

Od

0.87

OD

0.86

od

0.85

Od

0.84

Dod

0.84

oda

0.82

Activations Density 0.158%

terms related to biology, specifically taxonomy and classification

No Comments

No Known Activations