INDEX

Explanations

instances of the word "to" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

.dump

-0.14

subst

-0.14

spm

-0.14

.INSTANCE

-0.14

 nackte

-0.13

 callers

-0.13

 Kills

-0.13

iland

-0.13

rend

-0.13

ending

-0.13

POSITIVE LOGITS

IMUM

0.17

ä¾

0.16

vas

0.15

çĶ£

0.15

ocket

0.15

opc

0.14

oyo

0.14

rer

0.14

oldown

0.14

Ã£n

0.14

Activations Density 0.019%

instances of the word "to" in various contexts

No Comments

No Known Activations