INDEX

Explanations

instances of the word "teamed" and related variations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

marshall

-0.16

iki

-0.15

Ð°Ð¼ÐµÑĤ

-0.15

ffen

-0.15

agini

-0.14

luv

-0.14

 Orig

-0.14

uer

-0.14

itta

-0.14

.syntax

-0.14

POSITIVE LOGITS

hest

0.16

Ð±Ð¾ÑĢÐ°

0.15

igure

0.14

.Components

0.14

 settlement

0.14

 Settlement

0.14

Sov

0.14

RAR

0.14

olt

0.13

ÏĦÏİ

0.13

Activations Density 0.001%

instances of the word "teamed" and related variations

No Comments

No Known Activations