INDEX

Explanations

references to digital object identifiers (DOIs) used in academic and scientific literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

aval

-0.15

phet

-0.15

iky

-0.14

ople

-0.14

lod

-0.14

 Regional

-0.14

iesel

-0.13

pan

-0.13

apper

-0.13

uelle

-0.13

POSITIVE LOGITS

eland

0.15

 tisk

0.14

eyh

0.14

 openFileDialog

0.14

ULD

0.14

omo

0.14

ombat

0.14

annon

0.14

0.13

 Dtype

0.13

Activations Density 0.006%

references to digital object identifiers (DOIs) used in academic and scientific literature

No Comments

No Known Activations