INDEX

Explanations

references to TED Talks and their related components

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

fed

-0.15

[b

-0.15

cas

-0.14

igi

-0.14

arity

-0.14

.connector

-0.14

carry

-0.14

Ã¤r

-0.14

aga

-0.13

POSITIVE LOGITS

 Rosenstein

0.17

/Dk

0.15

REFIX

0.15

dne

0.14

ighth

0.14

.scalajs

0.14

.ToShort

0.14

claimer

0.14

Rog

0.13

 proofs

0.13

Activations Density 0.009%

references to TED Talks and their related components

No Comments

No Known Activations