INDEX

Explanations

occurrences of the letter "A" 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ale

-0.17

ALE

-0.16

ars

-0.15

ear

-0.15

ugin

-0.15

ony

-0.15

ation

-0.14

isa

-0.14

 Lean

-0.14

ophile

-0.14

POSITIVE LOGITS

-valu

0.17

 iddi

0.17

rouch

0.16

iot

0.16

 navr

0.15

imap

0.15

destruct

0.15

UDA

0.15

undles

0.14

 addCriterion

0.14

Activations Density 0.018%

occurrences of the letter "A" in various contexts

No Comments

No Known Activations