INDEX

Explanations

terms related to genes and genetic processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 genotype

-0.15

 Haupt

-0.15

 Skull

-0.14

\Mapping

-0.14

 Lomb

-0.14

Enumerable

-0.14

 voxel

-0.14

IBM

-0.14

div

-0.14

POSITIVE LOGITS

ERV

0.19

 tandem

0.19

.repeat

0.19

 repeat

0.17

LTR

0.17

 LINE

0.17

 silenced

0.17

quences

0.16

Repeat

0.16

 Silence

0.16

Activations Density 0.102%

terms related to genes and genetic processes

No Comments

No Known Activations